{"total":89,"rows":[{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2408.05147","title":"Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2","created":"2024-08-09","cited_by_count":394,"area":"mechinterp"},{"id":"2401.06102","title":"Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models","created":"2024-01-11","cited_by_count":235,"area":"mechinterp"},{"id":"2404.15255","title":"How to use and interpret activation patching","created":"2024-04-23","cited_by_count":214,"area":null},{"id":"2405.14860","title":"Not All Language Model Features Are One-Dimensionally Linear","created":"2024-05-23","cited_by_count":212,"area":null},{"id":"2403.17806","title":"Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms","created":"2024-03-26","cited_by_count":149,"area":null},{"id":"2410.07149","title":"Towards Interpreting Visual Information Processing in Vision-Language Models","created":"2024-10-09","cited_by_count":122,"area":"mllm"},{"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":"2402.14903","title":"Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs","created":"2024-02-22","cited_by_count":115,"area":null},{"id":"2403.00745","title":"AtP*: An efficient and scalable method for localizing LLM behaviour to components","created":"2024-03-01","cited_by_count":111,"area":"mechinterp"},{"id":"2410.21272","title":"Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics","created":"2024-10-28","cited_by_count":97,"area":"lr"},{"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":"2507.06203","title":"A Survey on Latent Reasoning","created":"2025-07-08","cited_by_count":81,"area":"lr"},{"id":"2410.13708","title":"On the Role of Attention Heads in Large Language Model Safety","created":"2024-10-17","cited_by_count":72,"area":"safety"},{"id":"2409.03752","title":"Attention Heads of Large Language Models: A Survey","created":"2024-09-05","cited_by_count":67,"area":null},{"id":"2406.16254","title":"Confidence Regulation Neurons in Language Models","created":"2024-06-24","cited_by_count":57,"area":null},{"id":"2504.13151","title":"MIB: A Mechanistic Interpretability Benchmark","created":"2025-04-17","cited_by_count":56,"area":"mechinterp"},{"id":"2601.04480","title":"When Models Manipulate Manifolds: The Geometry of a Counting Task","created":"2026-01-08","cited_by_count":46,"area":null},{"id":"2407.01178","title":"$\\text{Memory}^3$: Language Modeling with Explicit Memory","created":"2024-07-01","cited_by_count":40,"area":"rag"},{"id":"2407.15018","title":"Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions","created":"2024-07-21","cited_by_count":35,"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":"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":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2510.07358","title":"Encode, Think, Decode: Scaling test-time reasoning with recursive latent thoughts","created":"2025-10-08","cited_by_count":24,"area":"lr"},{"id":"2407.00886","title":"Efficient Automated Circuit Discovery in Transformers using Contextual Decomposition","created":"2024-07-01","cited_by_count":23,"area":"mechinterp"},{"id":"2502.10835","title":"Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models","created":"2025-02-15","cited_by_count":23,"area":"lr"},{"id":"2602.08169","title":"Spherical Steering: Geometry-Aware Activation Rotation for Language Models","created":"2026-02-09","cited_by_count":21,"area":null},{"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":"2412.04703","title":"Transformers Struggle to Learn to Search","created":"2024-12-06","cited_by_count":19,"area":null},{"id":"2411.19628","title":"Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings","created":"2024-11-29","cited_by_count":15,"area":"mllm"},{"id":"2502.01540","title":"What is a Number, That a Large Language Model May Know It?","created":"2025-02-03","cited_by_count":15,"area":null},{"id":"2308.01154","title":"Arithmetic with Language Models: from Memorization to Computation","created":"2023-08-02","cited_by_count":12,"area":null},{"id":"2410.20210","title":"Looking Beyond The Top-1: Transformers Determine Top Tokens In Order","created":"2024-10-26","cited_by_count":12,"area":null},{"id":"2410.15580","title":"Language Models are Symbolic Learners in Arithmetic","created":"2024-10-21","cited_by_count":11,"area":null},{"id":"2411.10950","title":"Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering","created":"2024-11-17","cited_by_count":11,"area":"mllm"},{"id":"2602.08783","title":"Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure","created":"2026-02-09","cited_by_count":11,"area":"lr"},{"id":"2410.22316","title":"Understanding Synthetic Context Extension via Retrieval Heads","created":"2024-10-29","cited_by_count":10,"area":"rag"},{"id":"2502.04667","title":"Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning","created":"2025-02-07","cited_by_count":10,"area":"lr"},{"id":"2503.10894","title":"HyperDAS: Towards Automating Mechanistic Interpretability with Hypernetworks","created":"2025-03-13","cited_by_count":9,"area":"mechinterp"},{"id":"2505.05145","title":"Understanding In-context Learning of Addition via Activation Subspaces","created":"2025-05-08","cited_by_count":8,"area":null},{"id":"2508.01916","title":"Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning","created":"2025-08-03","cited_by_count":8,"area":"mechinterp"},{"id":"2311.16173","title":"Conditions for Length Generalization in Learning Reasoning Skills","created":"2023-11-22","cited_by_count":7,"area":"lr"},{"id":"2405.17653","title":"InversionView: A General-Purpose Method for Reading Information from Neural Activations","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2411.16105","title":"Adaptive Circuit Behavior and Generalization in Mechanistic Interpretability","created":"2024-11-25","cited_by_count":7,"area":"mechinterp"},{"id":"2502.02790","title":"Leveraging the true depth of LLMs","created":"2025-02-05","cited_by_count":7,"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":"2603.02913","title":"Eliciting Numerical Predictive Distributions of LLMs Without Autoregression","created":"2026-03-03","cited_by_count":6,"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":"2505.17630","title":"Correcting Gradient-Based Circuit Localization via Interaction-Aware Backpropagation","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2411.16260","title":"Unraveling Arithmetic in Large Language Models: The Role of Algebraic Structures","created":"2024-11-25","cited_by_count":4,"area":"lr"},{"id":"2506.06686","title":"Learning Distribution-Wise Control in Representation Space for Language Models","created":"2025-06-07","cited_by_count":4,"area":null},{"id":"2511.17699","title":"Understanding Counting Mechanisms in Large Language and Vision-Language Models","created":"2025-11-21","cited_by_count":4,"area":"mllm"},{"id":"2601.00791","title":"Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning","created":"2026-01-02","cited_by_count":4,"area":"lr"},{"id":"2605.06076","title":"Navigating by Old Maps: The Pitfalls of Static Mechanistic Localization in LLM Post-Training","created":"2026-05-07","cited_by_count":4,"area":"mechinterp"},{"id":"2503.16401","title":"Exploring the Hidden Reasoning Process of Large Language Models by Misleading Them","created":"2025-03-20","cited_by_count":3,"area":"lr"},{"id":"2601.22510","title":"Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic","created":"2026-01-30","cited_by_count":3,"area":null},{"id":"2605.05176","title":"Understanding In-Context Learning for Nonlinear Regression with Transformers: Attention as Featurizer","created":"2026-05-06","cited_by_count":3,"area":null},{"id":"2605.09239","title":"Repeated-Token Counting Reveals a Dissociation Between Representations and Outputs","created":"2026-05-10","cited_by_count":3,"area":null},{"id":"2608.13567","title":"Modular Cognitive Architecture Emerges in Large Language Models","created":"2026-06-27","cited_by_count":3,"area":null},{"id":"2502.21123","title":"Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2504.00226","title":"Large Language Models in Numberland: A Quick Test of Their Numerical Reasoning Abilities","created":"2025-03-31","cited_by_count":2,"area":"lr"},{"id":"2504.07997","title":"BiasCause: Evaluate Socially Biased Causal Reasoning of Large Language Models","created":"2025-04-08","cited_by_count":2,"area":"lr"},{"id":"2505.12268","title":"$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks","created":"2025-05-18","cited_by_count":2,"area":"mechinterp"},{"id":"2507.09875","title":"Function Induction and Task Generalization: An Interpretability Study with Off-by-One Addition","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2508.20353","title":"DFAMS: Dynamic-flow guided Federated Alignment based Multi-prototype Search","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2510.13908","title":"Interpreting the Latent Structure of Operator Precedence in Language Models","created":"2025-10-14","cited_by_count":2,"area":"lr"},{"id":"2603.12270","title":"Task-Specific Knowledge Distillation via Intermediate Probes","created":"2026-02-18","cited_by_count":2,"area":"distill"},{"id":"2605.09129","title":"Data-driven Circuit Discovery for Interpretability of Language Models","created":"2026-05-09","cited_by_count":2,"area":"mechinterp"},{"id":"2410.02343","title":"Listening to the Wise Few: Query-Key Alignment Unlocks Latent Correct Answers in Large Language Models","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2410.08069","title":"Unlearning-based Neural Interpretations","created":"2024-10-10","cited_by_count":1,"area":"safety"},{"id":"2411.15281","title":"ElastiFormer: Learned Redundancy Reduction in Transformer via Self-Distillation","created":"2024-11-22","cited_by_count":1,"area":"lr"},{"id":"2510.09340","title":"Deductive Logic in Language Models: Horizontal vs Vertical Reasoning","created":"2025-10-10","cited_by_count":1,"area":"lr"},{"id":"2602.10416","title":"AI-rithmetic","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2605.03258","title":"The Right Answer, the Wrong Direction: Why Transformers Fail at Counting and How to Fix It","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2605.17770","title":"Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models","created":"2026-05-18","cited_by_count":1,"area":"lr"},{"id":"2605.22488","title":"Represented Is Not Computed: A Causal Test of Candidate Algorithmic Intermediates in a Transformer","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2608.13129","title":"Numeracy in Large Language Models: Fundamental Limitations and Paths to Improvement","created":"2026-08-13","cited_by_count":1,"area":"lr"},{"id":"2608.22332","title":"Mechanistic Interpretability of Chain-of-Thought Reasoning via Sequential Activation Patching","created":"2026-08-23","cited_by_count":1,"area":"lr"},{"id":"2411.10813","title":"Information Anxiety in Large Language Models","created":"2024-11-16","cited_by_count":0,"area":null},{"id":"2502.15090","title":"ExpertLens: Activation steering features are highly interpretable","created":"2025-02-20","cited_by_count":0,"area":"mechinterp"},{"id":"2506.23679","title":"Learning Modular Exponentiation with Transformers","created":"2025-06-30","cited_by_count":0,"area":"mechinterp"},{"id":"2604.11663","title":"Why Do Large Language Models Generate Harmful Content?","created":"2026-04-13","cited_by_count":0,"area":"safety"},{"id":"2604.15842","title":"Disentangling Mathematical Reasoning in LLMs: A Methodological Investigation of Internal Mechanisms","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2606.06840","title":"Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2606.07410","title":"A Comprehensive Anatomy of Human and DeepSeek-R1 LLM Mathematical Reasoning","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2609.28747","title":"Technical Manual for Toolkit for Confidence-Corpus Consistency, Corpus Absorption and Rule Learning via Fine-Tuning on a Fabricated Corpus","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.35822","title":"Tracing mechanisms of sycophantic agreement in language models","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.04017","title":"Slaying the Hydra: Interaction-Aware Circuit Discovery in Language Models","created":"2026-10-02","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}