{"total":85,"rows":[{"id":"2406.11944","title":"Transcoders Find Interpretable LLM Feature Circuits","created":"2024-06-17","cited_by_count":200,"area":"mechinterp"},{"id":"2406.19384","title":"The Remarkable Robustness of LLMs: Stages of Inference?","created":"2024-06-27","cited_by_count":146,"area":null},{"id":"2407.02646","title":"A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models","created":"2024-07-02","cited_by_count":118,"area":"mechinterp"},{"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":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2410.11414","title":"ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability","created":"2024-10-15","cited_by_count":101,"area":"rag"},{"id":"2405.15071","title":"Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization","created":"2024-05-23","cited_by_count":79,"area":"lr"},{"id":"2406.00799","title":"Get my drift? Catching LLM Task Drift with Activation Deltas","created":"2024-06-02","cited_by_count":72,"area":"rag"},{"id":"2407.10827","title":"LLM Circuit Analyses Are Consistent Across Training and Scale","created":"2024-07-15","cited_by_count":63,"area":null},{"id":"2405.17969","title":"Knowledge Circuits in Pretrained Transformers","created":"2024-05-28","cited_by_count":60,"area":"mechinterp"},{"id":"2406.16254","title":"Confidence Regulation Neurons in Language Models","created":"2024-06-24","cited_by_count":57,"area":null},{"id":"2405.15471","title":"Emergence of a High-Dimensional Abstraction Phase in Language Transformers","created":"2024-05-24","cited_by_count":56,"area":null},{"id":"2504.13151","title":"MIB: A Mechanistic Interpretability Benchmark","created":"2025-04-17","cited_by_count":56,"area":"mechinterp"},{"id":"2408.00113","title":"Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models","created":"2024-07-31","cited_by_count":51,"area":"mechinterp"},{"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":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34,"area":null},{"id":"2505.12886","title":"Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective","created":"2025-05-19","cited_by_count":34,"area":"lr"},{"id":"2411.15268","title":"ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models","created":"2024-11-22","cited_by_count":30,"area":"mllm"},{"id":"2405.18711","title":"Calibrating Reasoning in Language Models with Internal Consistency","created":"2024-05-29","cited_by_count":28,"area":"lr"},{"id":"2408.09503","title":"Out-of-distribution generalization via composition: a lens through induction heads in Transformers","created":"2024-08-18","cited_by_count":28,"area":null},{"id":"2410.16251","title":"Can Knowledge Editing Really Correct Hallucinations?","created":"2024-10-21","cited_by_count":28,"area":null},{"id":"2410.00153","title":"Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution","created":"2024-09-30","cited_by_count":27,"area":null},{"id":"2407.20224","title":"Can Editing LLMs Inject Harm?","created":"2024-07-29","cited_by_count":22,"area":"safety"},{"id":"2510.09782","title":"The Geometry of Reasoning: Flowing Logics in Representation Space","created":"2025-10-10","cited_by_count":21,"area":"lr"},{"id":"2502.11812","title":"Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis","created":"2025-02-17","cited_by_count":20,"area":null},{"id":"2409.04185","title":"Residual Stream Analysis with Multi-Layer SAEs","created":"2024-09-06","cited_by_count":19,"area":"mechinterp"},{"id":"2501.12934","title":"Correctness Assessment of Code Generated by Large Language Models Using Internal Representations","created":"2025-01-22","cited_by_count":17,"area":null},{"id":"2502.11019","title":"Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning","created":"2025-02-16","cited_by_count":16,"area":null},{"id":"2405.03205","title":"Anchored Answers: Unravelling Positional Bias in GPT-2's Multiple-Choice Questions","created":"2024-05-06","cited_by_count":15,"area":"mechinterp"},{"id":"2410.01434","title":"Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","cited_by_count":11,"area":null},{"id":"2502.15543","title":"ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation","created":"2025-02-21","cited_by_count":11,"area":"rag"},{"id":"2511.04527","title":"Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamics","created":"2025-11-06","cited_by_count":11,"area":"lr"},{"id":"2506.12880","title":"Universal Jailbreak Suffixes Are Strong Attention Hijackers","created":"2025-06-15","cited_by_count":10,"area":"safety"},{"id":"2512.08417","title":"Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs","created":"2025-12-09","cited_by_count":10,"area":"agents"},{"id":"2503.09066","title":"Probing Latent Subspaces in LLM for AI Security: Identifying and Manipulating Adversarial States","created":"2025-03-12","cited_by_count":9,"area":"safety"},{"id":"2509.17588","title":"Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models","created":"2025-09-22","cited_by_count":9,"area":"mllm"},{"id":"2601.04765","title":"Differential syntactic and semantic encoding in LLMs","created":"2026-01-08","cited_by_count":7,"area":null},{"id":"2406.06581","title":"Order-Independence Without Fine Tuning","created":"2024-06-04","cited_by_count":6,"area":null},{"id":"2406.17837","title":"Transformer Normalisation Layers and the Independence of Semantic Subspaces","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2410.06024","title":"Jet Expansions of Residual Computation","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2411.01663","title":"Unlocking the Theory Behind Scaling 1-Bit Neural Networks","created":"2024-11-03","cited_by_count":4,"area":null},{"id":"2412.16247","title":"Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models","created":"2024-12-20","cited_by_count":4,"area":null},{"id":"2505.11611","title":"Signal in the Noise: Polysemantic Interference Transfers and Predicts Cross-Model Influence","created":"2025-05-16","cited_by_count":4,"area":"mechinterp"},{"id":"2601.22012","title":"Putting a Face to Forgetting: Continual Learning meets Mechanistic Interpretability","created":"2026-01-29","cited_by_count":4,"area":"mechinterp"},{"id":"2605.01555","title":"Automated Interpretability and Feature Discovery in Language Models with Agents","created":"2026-05-02","cited_by_count":4,"area":"agents"},{"id":"2605.14075","title":"Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity","created":"2026-05-13","cited_by_count":4,"area":"lr"},{"id":"2504.16760","title":"Lightweight Latent Verifiers for Efficient Meta-Generation Strategies","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2505.24539","title":"Localizing Persona Representations in LLMs","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2509.25045","title":"Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures","created":"2025-09-29","cited_by_count":3,"area":"mechinterp"},{"id":"2603.03031","title":"Step-Level Sparse Autoencoder for Reasoning Process Interpretation","created":"2026-03-03","cited_by_count":3,"area":"lr"},{"id":"2408.00584","title":"Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses","created":"2024-08-01","cited_by_count":2,"area":null},{"id":"2501.15225","title":"SEAL: Scaling to Emphasize Attention for Long-Context Retrieval","created":"2025-01-25","cited_by_count":2,"area":null},{"id":"2507.09406","title":"Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers","created":"2025-07-12","cited_by_count":2,"area":"alignment"},{"id":"2510.17256","title":"Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations","created":"2025-10-20","cited_by_count":2,"area":"mechinterp"},{"id":"2512.22088","title":"Unifying Learning Dynamics and Generalization in Transformers Scaling Law","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2601.03657","title":"In Search of Grandmother Cells: Tracing Interpretable Neurons in Tabular Representations","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2603.22593","title":"Language Models Can Explain Visual Features via Steering","created":"2026-03-23","cited_by_count":2,"area":"mechinterp"},{"id":"2604.17761","title":"Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks","created":"2026-04-20","cited_by_count":2,"area":"mechinterp"},{"id":"2605.09129","title":"Data-driven Circuit Discovery for Interpretability of Language Models","created":"2026-05-09","cited_by_count":2,"area":"mechinterp"},{"id":"2608.24065","title":"Mechanistic Circuit Identification for Controllable Data Generation","created":"2026-08-25","cited_by_count":2,"area":null},{"id":"2506.16550","title":"A Free Probabilistic Framework for Analyzing the Transformer-based Language Models","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2509.18010","title":"Cross-Attention is Half Explanation in Speech-to-Text Models","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2510.09340","title":"Deductive Logic in Language Models: Horizontal vs Vertical Reasoning","created":"2025-10-10","cited_by_count":1,"area":"lr"},{"id":"2510.18462","title":"DePass: Unified Feature Attributing by Simple Decomposed Forward Pass","created":"2025-10-21","cited_by_count":1,"area":"mechinterp"},{"id":"2602.16608","title":"Explainable AI: Context-Aware Layer-Wise Integrated Gradients for Explaining Transformer Models","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2603.02919","title":"Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers","created":"2026-03-03","cited_by_count":1,"area":"diffusion"},{"id":"2604.00716","title":"CircuitProbe: Predicting Reasoning Circuits in Transformers via Stability Zone Detection","created":"2026-04-01","cited_by_count":1,"area":"lr"},{"id":"2604.06356","title":"In-Context Learning in Speech Language Models: Analyzing the Role of Acoustic Features, Linguistic Structure, and Induction Heads","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2608.22007","title":"The Communication Map of a Transformer","created":"2026-08-22","cited_by_count":1,"area":"mechinterp"},{"id":"2507.13858","title":"InTraVisTo: Inside Transformer Visualisation Tool","created":"2025-07-18","cited_by_count":0,"area":"lr"},{"id":"2510.11958","title":"Direct Multi-Token Decoding","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2601.22795","title":"Sparse or Dense? A Mechanistic Estimation of Computation Density in Transformer-based LLMs","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.02521","title":"Scaled Dot-Product Attention implements projection of inputs onto a common surface","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2604.07019","title":"ConceptTracer: Interactive Analysis of Concept Saliency and Selectivity in Neural Representations","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.19678","title":"Exploring Language-Agnosticity in Function Vectors: A Case Study in Machine Translation","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.11093","title":"Enabling Performant and Flexible Model-Internal Observability for LLM Inference","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.22532","title":"Relational Linear Properties in Language Models: An Empirical Investigation","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.01967","title":"Training Prompt Matters: State-Adaptive Optimization for Robust Fine-Tuning","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.07604","title":"Contribution Weights: A Geometrical Analysis of Self-Attention Transformers","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.02964","title":"Individual Parameters in Weight-Sparse Transformers Appear Interpretable","created":"2026-07-03","cited_by_count":0,"area":"mechinterp"},{"id":"2607.10803","title":"Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2608.07812","title":"On the use of foundation models in cognitive science","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.25555","title":"Virgil: Navigating Explainability for Transformer-based Language Models","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2610.10303","title":"On the Necessity of Attention-FFN Split in Vision Transformers","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}