{"total":102,"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":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231,"area":"alignment"},{"id":"2406.19384","title":"The Remarkable Robustness of LLMs: Stages of Inference?","created":"2024-06-27","cited_by_count":146,"area":null},{"id":"2407.12404","title":"Analyzing the Generalization and Reliability of Steering Vectors","created":"2024-07-17","cited_by_count":143,"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":"2402.16438","title":"Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models","created":"2024-02-26","cited_by_count":126,"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":"2410.13928","title":"Automatically Interpreting Millions of Features in Large Language Models","created":"2024-10-17","cited_by_count":113,"area":"mechinterp"},{"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":"2607.15495","title":"Verbalizable Representations Form a Global Workspace in Language Models","created":"2026-07-16","cited_by_count":75,"area":null},{"id":"2406.16254","title":"Confidence Regulation Neurons in Language Models","created":"2024-06-24","cited_by_count":57,"area":null},{"id":"2410.13835","title":"Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs","created":"2024-10-17","cited_by_count":56,"area":null},{"id":"2406.14144","title":"Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons","created":"2024-06-20","cited_by_count":53,"area":"alignment"},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"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":"2503.21073","title":"Shared Global and Local Geometry of Language Model Embeddings","created":"2025-03-27","cited_by_count":36,"area":null},{"id":"2410.06672","title":"Towards Universality: Studying Mechanistic Similarity Across Language Model Architectures","created":"2024-10-09","cited_by_count":31,"area":"ssm"},{"id":"2511.08579","title":"Training Language Models to Explain Their Own Computations","created":"2025-11-11","cited_by_count":30,"area":null},{"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":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2506.06609","title":"Transferring Linear Features Across Language Models With Model Stitching","created":"2025-06-07","cited_by_count":21,"area":"mechinterp"},{"id":"2406.12288","title":"An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs","created":"2024-06-18","cited_by_count":20,"area":"lr"},{"id":"2506.15679","title":"Dense SAE Latents Are Features, Not Bugs","created":"2025-06-18","cited_by_count":17,"area":"mechinterp"},{"id":"2405.02765","title":"Has this Fact been Edited? Detecting Knowledge Edits in Language Models","created":"2024-05-04","cited_by_count":14,"area":null},{"id":"2406.10868","title":"Identifying Query-Relevant Neurons in Large Language Models for Long-Form Texts","created":"2024-06-16","cited_by_count":14,"area":null},{"id":"2410.10360","title":"Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning","created":"2024-10-14","cited_by_count":14,"area":"rag"},{"id":"2503.07604","title":"Implicit Reasoning in Transformers is Reasoning through Shortcuts","created":"2025-03-10","cited_by_count":14,"area":"lr"},{"id":"2502.11856","title":"LLMs as a synthesis between symbolic and distributed approaches to language","created":"2025-02-17","cited_by_count":13,"area":null},{"id":"2504.02904","title":"How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence","created":"2025-04-03","cited_by_count":12,"area":null},{"id":"2504.08775","title":"Layers at Similar Depths Generate Similar Activations Across LLM Architectures","created":"2025-04-03","cited_by_count":12,"area":null},{"id":"2410.01288","title":"Mitigating Copy Bias in In-Context Learning through Neuron Pruning","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2510.05184","title":"Representation Potentials of Foundation Models for Multimodal Alignment: A Survey","created":"2025-10-05","cited_by_count":11,"area":null},{"id":"2605.06510","title":"Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models","created":"2026-05-07","cited_by_count":10,"area":null},{"id":"2507.14900","title":"From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons Alignment","created":"2025-07-20","cited_by_count":9,"area":null},{"id":"2511.00280","title":"Calibration Across Layers: Understanding Calibration Evolution in LLMs","created":"2025-10-31","cited_by_count":9,"area":null},{"id":"2408.15300","title":"GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs","created":"2024-08-27","cited_by_count":8,"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":"2402.09099","title":"Neuron-based Multifractal Analysis of Neuron Interaction Dynamics in Large Models","created":"2024-02-14","cited_by_count":7,"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":"2506.00653","title":"Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2507.02559","title":"Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability","created":"2025-07-03","cited_by_count":7,"area":"mechinterp"},{"id":"2405.15756","title":"Wasserstein Distances, Neuronal Entanglement, and Sparsity","created":"2024-05-24","cited_by_count":6,"area":"mechinterp"},{"id":"2508.16929","title":"Dimensional Collapse in Transformer Attention Outputs: A Challenge for Sparse Dictionary Learning","created":"2025-08-23","cited_by_count":6,"area":"mechinterp"},{"id":"2601.03115","title":"Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models","created":"2026-01-06","cited_by_count":6,"area":null},{"id":"2602.18458","title":"The Story is Not the Science: Execution-Grounded Evaluation of Mechanistic Interpretability Research","created":"2026-02-05","cited_by_count":6,"area":"mechinterp"},{"id":"2407.11215","title":"Mechanistic interpretability of large language models with applications to the financial services industry","created":"2024-07-15","cited_by_count":5,"area":"mechinterp"},{"id":"2501.15754","title":"Weight-based Analysis of Detokenization in Language Models: Understanding the First Stage of Inference Without Inference","created":"2025-01-27","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":"2601.10266","title":"Measuring Affinity between Attention-Head Weight Subspaces via the Projection Kernel","created":"2026-01-15","cited_by_count":5,"area":null},{"id":"2502.17355","title":"On Relation-Specific Neurons in Large Language Models","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2504.12585","title":"Identifying and Mitigating the Influence of the Prior Distribution in Large Language Models","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2510.03186","title":"Superposition disentanglement of neural representations reveals hidden alignment","created":"2025-10-03","cited_by_count":4,"area":"mechinterp"},{"id":"2604.04496","title":"The Indra Representation Hypothesis for Multimodal Alignment","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2604.13386","title":"Linear Probe Accuracy Scales with Model Size and Benefits from Multi-Layer Ensembling","created":"2026-04-15","cited_by_count":4,"area":"alignment"},{"id":"2404.13855","title":"Understanding the role of FFNs in driving multilingual behaviour in LLMs","created":"2024-04-22","cited_by_count":3,"area":null},{"id":"2505.13899","title":"Causes and Consequences of Representational Similarity in Machine Learning Models","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2506.04142","title":"Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2507.22918","title":"Semantic Convergence: Investigating Shared Representations Across Scaled LLMs","created":"2025-07-21","cited_by_count":3,"area":"mechinterp"},{"id":"2509.17866","title":"Understanding Post-Training Structural Changes in Large Language Models","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2509.25596","title":"Binary Sparse Coding for Interpretability","created":"2025-09-29","cited_by_count":3,"area":"mechinterp"},{"id":"2510.04500","title":"Expand Neurons, Not Parameters","created":"2025-10-06","cited_by_count":3,"area":null},{"id":"2510.24942","title":"Finding Culture-Sensitive Neurons in Vision-Language Models","created":"2025-10-28","cited_by_count":3,"area":"mllm"},{"id":"2604.06005","title":"Disentangling MLP Neuron Weights in Vocabulary Space","created":"2026-04-07","cited_by_count":3,"area":"mechinterp"},{"id":"2507.09185","title":"Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models","created":"2025-07-12","cited_by_count":2,"area":null},{"id":"2509.00928","title":"Superposition in Graph Neural Networks","created":"2025-08-31","cited_by_count":2,"area":null},{"id":"2509.24198","title":"Negative Pre-activations Differentiate Syntax","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2603.17231","title":"Neuron-Level Emotion Control in Speech-Generative Large Audio-Language Models","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2603.21607","title":"INTRYGUE: Induction-Aware Entropy Gating for Reliable RAG Uncertainty Estimation","created":"2026-03-23","cited_by_count":2,"area":"rag"},{"id":"2608.05164","title":"Cross-Architecture Steering Transfer in Language Models: A Systematic Empirical Study","created":"2026-05-26","cited_by_count":2,"area":"mechinterp"},{"id":"2407.10949","title":"Representing Rule-based Chatbots with Transformers","created":"2024-07-15","cited_by_count":1,"area":null},{"id":"2409.01610","title":"Decompose the model: Mechanistic interpretability in image models with Generalized Integrated Gradients (GIG)","created":"2024-09-03","cited_by_count":1,"area":"mechinterp"},{"id":"2411.07071","title":"Universal Response and Emergence of Induction in LLMs","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2505.16178","title":"Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2505.17936","title":"Understanding Gated Neurons in Transformers from Their Input-Output Functionality","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2507.18512","title":"Explaining How Visual, Textual and Multimodal Encoders Share Concepts","created":"2025-07-24","cited_by_count":1,"area":"mechinterp"},{"id":"2508.16109","title":"From Indirect Object Identification to Syllogisms: Exploring Binary Mechanisms in Transformer Circuits","created":"2025-08-22","cited_by_count":1,"area":"mechinterp"},{"id":"2509.10663","title":"Context Copying Modulation: The Role of Entropy Neurons in Managing Parametric and Contextual Knowledge Conflicts","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2601.04548","title":"Identifying Good and Bad Neurons for Task-Level Controllable LLMs","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2602.22600","title":"Transformers converge to invariant algorithmic cores","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2605.24942","title":"Riemannian-Manifold Steering: Geometry-Aware Generative Autoencoders for Label-Free Steering","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2606.03990","title":"Neuron Populations Exhibit Divergent Selectivity with Scale","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2607.11967","title":"Beyond Coordinate Gauge: An Audited Protocol for Detecting Donor-Specific Functional Fingerprints after Neural Collapse","created":"2026-07-12","cited_by_count":1,"area":null},{"id":"2608.08772","title":"Multilingual Emotion Neurons in Large Audio-Language Models","created":"2026-08-09","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":"2502.19669","title":"Investigating Neurons and Heads in Transformer-based LLMs for Typographical Errors","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2508.00903","title":"Universal Neurons in GPT-2: Emergence, Persistence, and Functional Impact","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2510.04285","title":"Probing Geometry of Next Token Prediction Using Cumulant Expansion of the Softmax Entropy","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2510.19427","title":"Revisiting the Relation Between Robustness and Universality","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2601.07473","title":"AntiPaSTO: Self-Supervised Honesty Steering via Anti-Parallel Representations","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2602.23826","title":"GLUScope: A Tool for Analyzing GLU Neurons in Transformer Language Models","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2605.09438","title":"fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.18808","title":"Compositional Literary Primitives in Instruction-Tuned LLMs: Cross-Architectural SAE Features for Self, Style, and Affect","created":"2026-05-11","cited_by_count":0,"area":"mechinterp"},{"id":"2607.17513","title":"After the Euclidean Highway: Hyperbolic Expert AI as the Next Innovation","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.21491","title":"What, Where, and How: Disentangling the Roles of Task, Language, and Model in Code Model Representations","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.17102","title":"Emotion Across Speech and Faces: Shared Affective Mechanisms in Multimodal Foundation Models","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.02959","title":"The Geometry of Ignorance: LLMs Know When to Temper Bayesian Priors","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.08173","title":"Key Path Identification for Resolving Knowledge Conflicts via SAE-based Steering","created":"2026-09-08","cited_by_count":0,"area":"mechinterp"},{"id":"2609.18612","title":"Weakening Neurons: An Input-Output Functionality in Transformers with Outsize Influence","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":"100"}