{"total":132,"rows":[{"id":"2405.14860","title":"Not All Language Model Features Are One-Dimensionally Linear","created":"2024-05-23","cited_by_count":212,"area":null},{"id":"2410.13787","title":"Looking Inward: Language Models Can Learn About Themselves by Introspection","created":"2024-10-17","cited_by_count":113,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2607.15495","title":"Verbalizable Representations Form a Global Workspace in Language Models","created":"2026-07-16","cited_by_count":75,"area":null},{"id":"2407.10827","title":"LLM Circuit Analyses Are Consistent Across Training and Scale","created":"2024-07-15","cited_by_count":63,"area":null},{"id":"2501.06346","title":"Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages","created":"2025-01-10","cited_by_count":59,"area":null},{"id":"2604.07729","title":"Emotion Concepts and their Function in a Large Language Model","created":"2026-04-09","cited_by_count":57,"area":null},{"id":"2510.26243","title":"Angular Steering: Behavior Control via Rotation in Activation Space","created":"2025-10-30","cited_by_count":53,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2505.11711","title":"Reinforcement Learning Finetunes Small Subnetworks in Large Language Models","created":"2025-05-16","cited_by_count":49,"area":null},{"id":"2408.10920","title":"Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations","created":"2024-08-20","cited_by_count":47,"area":null},{"id":"2407.14561","title":"NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals","created":"2024-07-18","cited_by_count":45,"area":null},{"id":"2406.09519","title":"Talking Heads: Understanding Inter-layer Communication in Transformer Language Models","created":"2024-06-13","cited_by_count":41,"area":null},{"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":"2406.19370","title":"Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2408.07144","title":"Language Models as Models of Language","created":"2024-08-13","cited_by_count":24,"area":null},{"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":"2407.04690","title":"Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpreting Neural Networks","created":"2024-07-05","cited_by_count":23,"area":null},{"id":"2502.11196","title":"How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training","created":"2025-02-16","cited_by_count":23,"area":null},{"id":"2602.08169","title":"Spherical Steering: Geometry-Aware Activation Rotation for Language Models","created":"2026-02-09","cited_by_count":21,"area":null},{"id":"2506.20790","title":"Stochastic Parameter Decomposition","created":"2025-06-25","cited_by_count":16,"area":null},{"id":"2502.01954","title":"Constrained belief updates explain geometric structures in transformer representations","created":"2025-02-04","cited_by_count":15,"area":null},{"id":"2407.03779","title":"Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity","created":"2024-07-04","cited_by_count":14,"area":null},{"id":"2511.22662","title":"Difficulties with Evaluating a Deception Detector for AIs","created":"2025-11-27","cited_by_count":13,"area":null},{"id":"2512.24440","title":"Towards mechanistic understanding in a data-driven weather model: internal activations reveal interpretable physical features","created":"2025-12-30","cited_by_count":12,"area":null},{"id":"2410.22590","title":"Characterizing the Role of Similarity in the Property Inferences of Language Models","created":"2024-10-29","cited_by_count":11,"area":null},{"id":"2503.11302","title":"Are formal and functional linguistic mechanisms dissociated in language models?","created":"2025-03-14","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":"2604.19117","title":"LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit","created":"2026-04-21","cited_by_count":10,"area":null},{"id":"2507.23221","title":"A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations","created":"2025-07-31","cited_by_count":9,"area":null},{"id":"2512.17639","title":"Linear Personality Probing and Steering in LLMs: A Big Five Study","created":"2025-12-19","cited_by_count":9,"area":null},{"id":"2509.17196","title":"Evolution of Concepts in Language Model Pre-Training","created":"2025-09-21","cited_by_count":8,"area":null},{"id":"2510.01025","title":"Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2512.03676","title":"Different types of syntactic agreement recruit the same units within large language models","created":"2025-12-03","cited_by_count":8,"area":null},{"id":"2602.16698","title":"Causality is Key for Interpretability Claims to Generalise","created":"2026-02-18","cited_by_count":8,"area":null},{"id":"2405.17420","title":"Survival of the Fittest Representation: A Case Study with Modular Addition","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2507.21141","title":"The Geometry of Harmfulness in LLMs through Subconcept Probing","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2512.15134","title":"From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?","created":"2025-12-17","cited_by_count":7,"area":null},{"id":"2606.07612","title":"Position: Anthropomorphic Misalignment Research Needs Stronger Evidence","created":"2026-05-29","cited_by_count":7,"area":null},{"id":"2509.05291","title":"Crosscoding Through Time: Tracking Emergence & Consolidation Of Linguistic Representations Throughout LLM Pretraining","created":"2025-09-05","cited_by_count":6,"area":null},{"id":"2601.19375","title":"Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection","created":"2026-01-27","cited_by_count":6,"area":null},{"id":"2604.12493","title":"Latent Planning Emerges with Scale","created":"2026-04-14","cited_by_count":6,"area":null},{"id":"2410.22944","title":"Focus On This, Not That! Steering LLMs with Adaptive Feature Specification","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2502.06809","title":"Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2504.15471","title":"Bigram Subnetworks: Mapping to Next Tokens in Transformer Language Models","created":"2025-04-21","cited_by_count":5,"area":null},{"id":"2605.01048","title":"Compared to What? Baselines and Metrics for Counterfactual Prompting","created":"2026-05-01","cited_by_count":5,"area":null},{"id":"2410.00340","title":"Sparse Attention Decomposition Applied to Circuit Tracing","created":"2024-10-01","cited_by_count":4,"area":null},{"id":"2412.05353","title":"Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models","created":"2024-12-06","cited_by_count":4,"area":null},{"id":"2505.15811","title":"On the creation of narrow AI: hierarchy and nonlocality of neural network skills","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2505.16505","title":"Sparse Activation Editing for Reliable Instruction Following in Narratives","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2506.01042","title":"Probing Neural Topology of Large Language Models","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2509.06938","title":"From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers","created":"2025-09-08","cited_by_count":4,"area":null},{"id":"2605.29889","title":"Where Do Apparent LLM Clinical Triage Failures Arise? Localizing the Multiple-Choice Format Effect","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2505.14406","title":"Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2506.15617","title":"The Compositional Architecture of Regret in Large Language Models","created":"2025-06-18","cited_by_count":3,"area":null},{"id":"2602.05184","title":"Towards Worst-Case Guarantees with Scale-Aware Interpretability","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2604.05090","title":"Multilingual Language Models Encode Script Over Linguistic Structure","created":"2026-04-06","cited_by_count":3,"area":null},{"id":"2406.03947","title":"Weight-based Decomposition: A Case for Bilinear MLPs","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2406.17241","title":"Understanding Language Model Circuits through Knowledge Editing","created":"2024-06-25","cited_by_count":2,"area":null},{"id":"2503.05424","title":"Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2508.18098","title":"Detecting and Characterizing Planning in Language Models","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2511.07002","title":"Automated Attribution Graph Interpretation via Probe Prompting","created":"2025-11-10","cited_by_count":2,"area":null},{"id":"2603.10771","title":"Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2604.10158","title":"Tracing the Thought of a Grandmaster-level Chess-Playing Transformer","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2604.16656","title":"Defragmenting Language Models: An Interpretability-based Approach for Vocabulary Expansion","created":"2026-04-17","cited_by_count":2,"area":null},{"id":"2605.11167","title":"The Bicameral Model: Bidirectional Hidden-State Coupling Between Parallel Language Models","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2606.07560","title":"Function-Vector Heads Are Two Populations: Writers and Cancellers in In-Context Learning","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2607.18921","title":"Circuit Claims Depend on What Is Extracted and How It Is Compared","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2608.26511","title":"Sycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Update","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2608.27540","title":"Towards a mathematical theory of superposition","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2407.10949","title":"Representing Rule-based Chatbots with Transformers","created":"2024-07-15","cited_by_count":1,"area":null},{"id":"2409.13163","title":"Hidden Activations Are Not Enough: A General Approach to Neural Network Predictions","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2411.07071","title":"Universal Response and Emergence of Induction in LLMs","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2504.03847","title":"Interpretable Multimodal Learning for Tumor Protein-Metal Binding: Progress, Challenges, and Perspectives","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2505.10719","title":"Tracr-Injection: Distilling Algorithms into Pre-trained Language Models","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2505.11576","title":"Concept-Guided Interpretability via Neural Chunking","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2507.10855","title":"Sparse Fine-Tuning of Transformers for Generative Tasks","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2509.24815","title":"Efficient Sketching and Nearest Neighbor Search Algorithms for Sparse Vector Sets","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2512.20796","title":"Measuring Mechanistic Independence: Can Bias Be Removed Without Erasing Demographics?","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2601.04098","title":"Layer-wise Positional Bias in Short-Context Language Modeling","created":"2026-01-07","cited_by_count":1,"area":null},{"id":"2601.19926","title":"The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2604.13218","title":"Identifiability of Potentially Degenerate Gaussian Mixture Models With Piecewise Affine Mixing","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2604.15010","title":"What Is the Minimum Architecture for Prolepsis? Early Irrevocable Commitment Across Tasks in Small Transformers","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.00333","title":"Borrowed Geometry: Cross-Distribution Head-Importance Fingerprints of Frozen Pretrained Gemma 4 31B","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2605.12809","title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.16331","title":"Retrieval and competition: how a protein foundation model starts a protein","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2607.08946","title":"Training, Reading, and Editing Legible Transformers","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2607.11347","title":"Do Neural Networks Preserve Case Structure? Case-Based Decomposition, Interpretation, and Decision Consistency","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2607.11990","title":"Sparse Inter-Layer Dependencies of Transformer FFN Neurons","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2608.19211","title":"Represented but Ignored: A Causal Account of Prosodic Underuse in Audio-Language Models","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2608.29458","title":"Reference-Grafting Matches Fine-Tuning at Eliciting Sandbagged Capabilities","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2609.10210","title":"Through the Looking Glass: Directly Reading and Writing Transformers","created":"2026-09-09","cited_by_count":1,"area":null},{"id":"2412.02893","title":"Removing Spurious Correlation from Neural Network Interpretations","created":"2024-12-03","cited_by_count":0,"area":null},{"id":"2502.01803","title":"Discovering Chunks in Neural Embeddings for Interpretability","created":"2025-02-03","cited_by_count":0,"area":null},{"id":"2502.05407","title":"Dictionary Learning: The Complexity of Learning Sparse Superposed Features with Feedback","created":"2025-02-08","cited_by_count":0,"area":null},{"id":"2504.21047","title":"Model Connectomes: A Generational Approach to Data-Efficient Language Models","created":"2025-04-29","cited_by_count":0,"area":null},{"id":"2506.06208","title":"Building Models of Neurological Language","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2507.10106","title":"BlueGlass: A Framework for Composite AI Safety","created":"2025-07-14","cited_by_count":0,"area":null}],"next_cursor":"100"}