{"total":394,"rows":[{"id":"2501.17148","title":"AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders","created":"2025-01-28","cited_by_count":218,"area":"mechinterp"},{"id":"2409.14507","title":"A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders","created":"2024-09-22","cited_by_count":160,"area":"mechinterp"},{"id":"2410.20526","title":"Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders","created":"2024-10-27","cited_by_count":143,"area":"mechinterp"},{"id":"2503.17547","title":"Learning Multi-Level Features with Matryoshka Sparse Autoencoders","created":"2025-03-21","cited_by_count":143,"area":"mechinterp"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2503.09532","title":"SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability","created":"2025-03-12","cited_by_count":124,"area":"mechinterp"},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121,"area":null},{"id":"2411.14257","title":"Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models","created":"2024-11-21","cited_by_count":115,"area":"mechinterp"},{"id":"2410.13928","title":"Automatically Interpreting Millions of Features in Large Language Models","created":"2024-10-17","cited_by_count":113,"area":"mechinterp"},{"id":"2411.02193","title":"Improving Steering Vectors by Targeting Sparse Autoencoder Features","created":"2024-11-04","cited_by_count":92,"area":"mechinterp"},{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2505.20063","title":"SAEs Are Good for Steering -- If You Select the Right Features","created":"2025-05-26","cited_by_count":78,"area":"mechinterp"},{"id":"2412.05276","title":"Sparse autoencoders reveal selective remapping of visual concepts during adaptation","created":"2024-12-06","cited_by_count":68,"area":"mechinterp"},{"id":"2503.01822","title":"Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry","created":"2025-03-03","cited_by_count":61,"area":"mechinterp"},{"id":"2502.20578","title":"Interpreting CLIP with Hierarchical Sparse Autoencoders","created":"2025-02-27","cited_by_count":60,"area":"mechinterp"},{"id":"2410.19278","title":"Applying sparse autoencoders to unlearn knowledge in language models","created":"2024-10-25","cited_by_count":59,"area":"safety"},{"id":"2504.13151","title":"MIB: A Mechanistic Interpretability Benchmark","created":"2025-04-17","cited_by_count":56,"area":"mechinterp"},{"id":"2410.19750","title":"The Geometry of Concepts: Sparse Autoencoder Feature Structure","created":"2024-10-10","cited_by_count":52,"area":"mechinterp"},{"id":"2506.07022","title":"AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint","created":"2025-06-08","cited_by_count":49,"area":"safety"},{"id":"2410.14670","title":"Decomposing The Dark Matter of Sparse Autoencoders","created":"2024-10-18","cited_by_count":45,"area":"mechinterp"},{"id":"2503.18878","title":"I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders","created":"2025-03-24","cited_by_count":45,"area":"lr"},{"id":"2501.08319","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions","created":"2025-01-14","cited_by_count":41,"area":null},{"id":"2507.16795","title":"Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning","created":"2025-07-22","cited_by_count":39,"area":null},{"id":"2502.08524","title":"LLM Pretraining with Continuous Concepts","created":"2025-02-12","cited_by_count":36,"area":"lr"},{"id":"2501.09929","title":"Interpretable Steering of Large Language Models with Feature Guided Activation Additions","created":"2025-01-17","cited_by_count":35,"area":"mechinterp"},{"id":"2409.04478","title":"Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small","created":"2024-09-05","cited_by_count":34,"area":"mechinterp"},{"id":"2410.22366","title":"One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models","created":"2024-10-28","cited_by_count":33,"area":"diffusion"},{"id":"2411.04430","title":"Towards Unifying Interpretability and Control: Evaluation via Intervention","created":"2024-11-07","cited_by_count":32,"area":"mechinterp"},{"id":"2511.08579","title":"Training Language Models to Explain Their Own Computations","created":"2025-11-11","cited_by_count":30,"area":null},{"id":"2505.16188","title":"SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models","created":"2025-05-22","cited_by_count":29,"area":"mechinterp"},{"id":"2505.23556","title":"Understanding Refusal in Language Models with Sparse Autoencoders","created":"2025-05-29","cited_by_count":29,"area":"alignment"},{"id":"2506.05744","title":"Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties","created":"2025-06-06","cited_by_count":29,"area":"lr"},{"id":"2410.06981","title":"Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders","created":"2024-10-09","cited_by_count":27,"area":"mechinterp"},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2503.03730","title":"Towards Understanding Distilled Reasoning Models: A Representational Approach","created":"2025-03-05","cited_by_count":26,"area":"lr"},{"id":"2503.08200","title":"Route Sparse Autoencoder to Interpret Large Language Models","created":"2025-03-11","cited_by_count":26,"area":"mechinterp"},{"id":"2602.02132","title":"There Is More to Refusal in Large Language Models than a Single Direction","created":"2026-02-02","cited_by_count":26,"area":"mechinterp"},{"id":"2506.11976","title":"How Visual Representations Map to Language Feature Space in Multimodal LLMs","created":"2025-06-13","cited_by_count":25,"area":"lr"},{"id":"2601.22594","title":"Language Model Circuits Are Sparse in the Neuron Basis","created":"2026-01-30","cited_by_count":25,"area":"mechinterp"},{"id":"2503.07639","title":"Mixture of Experts Made Intrinsically Interpretable","created":"2025-03-05","cited_by_count":24,"area":"moe"},{"id":"2505.20322","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","created":"2025-05-23","cited_by_count":24,"area":null},{"id":"2506.03292","title":"HyperSteer: Activation Steering at Scale with Hypernetworks","created":"2025-06-03","cited_by_count":23,"area":"mechinterp"},{"id":"2410.07656","title":"Mechanistic Permutability: Match Features Across Layers","created":"2024-10-10","cited_by_count":22,"area":"mechinterp"},{"id":"2411.02335","title":"Sparsing Law: Towards Large Language Models with Greater Activation Sparsity","created":"2024-11-04","cited_by_count":22,"area":null},{"id":"2504.08192","title":"SAEs Can Improve Unlearning: Dynamic Sparse Autoencoder Guardrails for Precision Unlearning in LLMs","created":"2025-04-11","cited_by_count":22,"area":"safety"},{"id":"2502.11367","title":"Sparse Autoencoder Features for Classifications and Transferability","created":"2025-02-17","cited_by_count":21,"area":"mechinterp"},{"id":"2502.15576","title":"Interpreting and Steering LLMs with Mutual Information-based Explanations on Sparse Autoencoders","created":"2025-02-21","cited_by_count":21,"area":"mechinterp"},{"id":"2506.06609","title":"Transferring Linear Features Across Language Models With Model Stitching","created":"2025-06-07","cited_by_count":21,"area":"mechinterp"},{"id":"2605.11887","title":"Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models","created":"2026-05-12","cited_by_count":21,"area":"mechinterp"},{"id":"2409.04185","title":"Residual Stream Analysis with Multi-Layer SAEs","created":"2024-09-06","cited_by_count":19,"area":"mechinterp"},{"id":"2411.08790","title":"Can sparse autoencoders be used to decompose and interpret steering vectors?","created":"2024-11-13","cited_by_count":19,"area":"mechinterp"},{"id":"2505.14352","title":"Towards eliciting latent knowledge from LLMs with mechanistic interpretability","created":"2025-05-20","cited_by_count":19,"area":"mechinterp"},{"id":"2410.01174","title":"Towards Inference-time Category-wise Safety Steering for Large Language Models","created":"2024-10-02","cited_by_count":18,"area":"alignment"},{"id":"2411.13117","title":"Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders","created":"2024-11-20","cited_by_count":18,"area":"mechinterp"},{"id":"2501.06254","title":"Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words","created":"2025-01-09","cited_by_count":18,"area":"lr"},{"id":"2505.24428","title":"Model Unlearning via Sparse Autoencoder Subspace Guided Projections","created":"2025-05-30","cited_by_count":18,"area":"safety"},{"id":"2410.11767","title":"Analyzing (In)Abilities of SAEs via Formal Languages","created":"2024-10-15","cited_by_count":17,"area":"mechinterp"},{"id":"2506.15679","title":"Dense SAE Latents Are Features, Not Bugs","created":"2025-06-18","cited_by_count":17,"area":"mechinterp"},{"id":"2507.09709","title":"Large Language Models Encode Semantics and Alignment in Linearly Separable Representations","created":"2025-07-13","cited_by_count":17,"area":"safety"},{"id":"2411.00743","title":"Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models","created":"2024-11-01","cited_by_count":16,"area":"mechinterp"},{"id":"2505.11756","title":"Feature Hedging: Correlated Features Break Narrow Sparse Autoencoders","created":"2025-05-16","cited_by_count":16,"area":"mechinterp"},{"id":"2410.01280","title":"Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models","created":"2024-10-02","cited_by_count":15,"area":"mechinterp"},{"id":"2503.03601","title":"Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders","created":"2025-03-05","cited_by_count":15,"area":"mechinterp"},{"id":"2505.17815","title":"Evaluation Faking: Unveiling Observer Effects in Safety Evaluation of Frontier AI Systems","created":"2025-05-23","cited_by_count":14,"area":"lr"},{"id":"2506.01197","title":"Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures","created":"2025-06-01","cited_by_count":14,"area":"mechinterp"},{"id":"2506.15963","title":"On the Limits of Sparse Autoencoders: A Theoretical Framework and Reweighted Remedy","created":"2025-06-19","cited_by_count":14,"area":"mechinterp"},{"id":"2508.16560","title":"Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders","created":"2025-08-22","cited_by_count":14,"area":"mechinterp"},{"id":"2602.14111","title":"Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?","created":"2026-02-15","cited_by_count":14,"area":"mechinterp"},{"id":"2410.21331","title":"Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness","created":"2024-10-27","cited_by_count":13,"area":null},{"id":"2412.04139","title":"Monet: Mixture of Monosemantic Experts for Transformers","created":"2024-12-05","cited_by_count":13,"area":"mechinterp"},{"id":"2502.03032","title":"Analyze Feature Flow to Enhance Interpretation and Steering in Language Models","created":"2025-02-05","cited_by_count":13,"area":"mechinterp"},{"id":"2502.16994","title":"FADE: Why Bad Descriptions Happen to Good Features","created":"2025-02-24","cited_by_count":13,"area":"mechinterp"},{"id":"2505.15634","title":"Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models","created":"2025-05-21","cited_by_count":13,"area":"lr"},{"id":"2506.08390","title":"On Reasoning Strength Planning in Large Reasoning Models","created":"2025-06-10","cited_by_count":13,"area":"lr"},{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2411.07618","title":"Constrain Alignment with Sparse Autoencoders","created":"2024-11-12","cited_by_count":12,"area":"alignment"},{"id":"2502.14044","title":"Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data","created":"2025-02-19","cited_by_count":12,"area":"mllm"},{"id":"2502.14050","title":"Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder","created":"2025-02-19","cited_by_count":12,"area":"mechinterp"},{"id":"2506.07335","title":"Improving LLM Reasoning through Interpretable Role-Playing Steering","created":"2025-06-09","cited_by_count":12,"area":"lr"},{"id":"2508.12535","title":"CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features","created":"2025-08-18","cited_by_count":12,"area":"mechinterp"},{"id":"2601.05679","title":"Do Sparse Autoencoders Identify Reasoning Features in Language Models?","created":"2026-01-09","cited_by_count":12,"area":"lr"},{"id":"2602.02464","title":"From Directions to Regions: Decomposing Activations in Language Models via Local Geometry","created":"2026-02-02","cited_by_count":12,"area":null},{"id":"2410.21508","title":"Group-SAE: Efficient Training of Sparse Autoencoders for Large Language Models via Layer Groups","created":"2024-10-28","cited_by_count":11,"area":"mechinterp"},{"id":"2412.01113","title":"LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-step Arithmetics","created":"2024-12-02","cited_by_count":11,"area":"lr"},{"id":"2504.07440","title":"Model Utility Law: Evaluating LLMs beyond Performance through Mechanism Interpretable Metric","created":"2025-04-10","cited_by_count":11,"area":null},{"id":"2505.22586","title":"Precise In-Parameter Concept Erasure in Large Language Models","created":"2025-05-28","cited_by_count":11,"area":null},{"id":"2505.24650","title":"Beyond the Black Box: Interpretability of LLMs in Finance","created":"2025-05-14","cited_by_count":11,"area":"mechinterp"},{"id":"2509.02565","title":"Understanding sparse autoencoder scaling in the presence of feature manifolds","created":"2025-09-02","cited_by_count":11,"area":"mechinterp"},{"id":"2602.14161","title":"When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift","created":"2026-02-15","cited_by_count":11,"area":"agents"},{"id":"2506.05451","title":"Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety","created":"2025-06-05","cited_by_count":10,"area":"safety"},{"id":"2506.15538","title":"Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework","created":"2025-06-18","cited_by_count":10,"area":null},{"id":"2507.00711","title":"Large Reasoning Models are not thinking straight: on the unreliability of thinking trajectories","created":"2025-07-01","cited_by_count":10,"area":"lr"},{"id":"2511.20820","title":"SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models","created":"2025-11-25","cited_by_count":10,"area":"agents"},{"id":"2605.07990","title":"Tool Calling is Linearly Readable and Steerable in Language Models","created":"2026-05-08","cited_by_count":10,"area":"agents"},{"id":"2504.20938","title":"Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition","created":"2025-04-29","cited_by_count":9,"area":"mechinterp"},{"id":"2505.14071","title":"Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models","created":"2025-05-20","cited_by_count":9,"area":"mllm"},{"id":"2505.14536","title":"Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders","created":"2025-05-20","cited_by_count":9,"area":"mechinterp"},{"id":"2505.15038","title":"Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering","created":"2025-05-21","cited_by_count":9,"area":"mechinterp"},{"id":"2502.19964","title":"Do Sparse Autoencoders Generalize? A Case Study of Answerability","created":"2025-02-27","cited_by_count":8,"area":"mechinterp"},{"id":"2503.03032","title":"SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs","created":"2025-03-04","cited_by_count":8,"area":"mechinterp"}],"next_cursor":"100"}