{"total":54,"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":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197,"area":null},{"id":"2405.13954","title":"What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions","created":"2024-05-22","cited_by_count":94,"area":null},{"id":"2504.13151","title":"MIB: A Mechanistic Interpretability Benchmark","created":"2025-04-17","cited_by_count":56,"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":"2406.19501","title":"Monitoring Latent World States in Language Models with Propositional Probes","created":"2024-06-27","cited_by_count":43,"area":"wm"},{"id":"2507.08802","title":"The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?","created":"2025-07-11","cited_by_count":37,"area":"mechinterp"},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36,"area":"alignment"},{"id":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2411.07404","title":"Controllable Context Sensitivity and the Knob Behind It","created":"2024-11-11","cited_by_count":23,"area":null},{"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":"2506.03292","title":"HyperSteer: Activation Steering at Scale with Hypernetworks","created":"2025-06-03","cited_by_count":23,"area":"mechinterp"},{"id":"2406.16033","title":"Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models","created":"2024-06-23","cited_by_count":22,"area":"mechinterp"},{"id":"2410.10343","title":"Locking Down the Finetuned LLMs Safety","created":"2024-10-14","cited_by_count":22,"area":null},{"id":"2505.16002","title":"Causal Interventions Reveal Shared Structure Across English Filler-Gap Constructions","created":"2025-05-21","cited_by_count":21,"area":null},{"id":"2404.00216","title":"Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness","created":"2024-03-30","cited_by_count":17,"area":null},{"id":"2406.15955","title":"Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects","created":"2024-06-22","cited_by_count":13,"area":null},{"id":"2502.03799","title":"Enhancing Hallucination Detection through Noise Injection","created":"2025-02-06","cited_by_count":13,"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":"2605.29548","title":"Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention","created":"2026-05-28","cited_by_count":10,"area":null},{"id":"2505.15105","title":"Mechanistic evaluation of Transformers and state space models","created":"2025-05-21","cited_by_count":9,"area":"ssm"},{"id":"2507.21141","title":"The Geometry of Harmfulness in LLMs through Subconcept Probing","created":"2025-07-23","cited_by_count":7,"area":null},{"id":"2511.04638","title":"Addressing divergent representations from causal interventions on neural networks","created":"2025-11-06","cited_by_count":7,"area":"mechinterp"},{"id":"2506.18141","title":"Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models","created":"2025-06-22","cited_by_count":6,"area":"mechinterp"},{"id":"2508.02513","title":"Modular Arithmetic: Language Models Solve Math Digit by Digit","created":"2025-08-04","cited_by_count":6,"area":null},{"id":"2408.00211","title":"Penzai + Treescope: A Toolkit for Interpreting, Visualizing, and Editing Models As Data","created":"2024-08-01","cited_by_count":5,"area":null},{"id":"2504.06303","title":"On the Effectiveness and Generalization of Race Representations for Debiasing High-Stakes Decisions","created":"2025-04-07","cited_by_count":5,"area":null},{"id":"2503.11429","title":"Combining Causal Models for More Accurate Abstractions of Neural Networks","created":"2025-03-14","cited_by_count":4,"area":"mechinterp"},{"id":"2506.03978","title":"Structured Pruning for Diverse Best-of-N Reasoning Optimization","created":"2025-06-04","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":"2511.14465","title":"nnterp: A Standardized Interface for Mechanistic Interpretability of Transformers","created":"2025-11-18","cited_by_count":2,"area":"mechinterp"},{"id":"2602.06022","title":"Correctness-Optimized Residual Activation Lens (CORAL): Transferrable and Calibration-Aware Inference-Time Steering","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2603.07837","title":"AI Steerability 360: A Toolkit for Steering Large Language Models","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2508.10553","title":"eDIF: A European Deep Inference Fabric for Remote Interpretability of LLM","created":"2025-08-14","cited_by_count":1,"area":"mechinterp"},{"id":"2512.09730","title":"Interpreto: An Explainability Library for Transformers","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2602.23993","title":"The GRADIEND Python Package: An End-to-End System for Gradient-Based Feature Learning","created":"2026-02-27","cited_by_count":1,"area":null},{"id":"2605.02234","title":"Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction","created":"2026-05-04","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":"2607.16693","title":"Are Arithmetic Heuristic Neurons Form-Invariant? A Mechanistic Analysis of Symbols, Text, and Code in LLMs","created":"2026-07-18","cited_by_count":1,"area":"mechinterp"},{"id":"2609.03026","title":"ObserverBench: Testing Mechanistic Estimates for Intervention and Control","created":"2026-09-02","cited_by_count":1,"area":"mechinterp"},{"id":"2407.21656","title":"Comgra: A Tool for Analyzing and Debugging Neural Networks","created":"2024-07-31","cited_by_count":0,"area":null},{"id":"2506.04774","title":"Fine-Grained Interpretation of Political Opinions in Large Language Models","created":"2025-06-05","cited_by_count":0,"area":"mechinterp"},{"id":"2509.25475","title":"TDHook: A Lightweight Framework for Interpretability","created":"2025-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2604.13950","title":"Causal Drawbridges: Characterizing Gradient Blocking of Syntactic Islands in Transformer LMs","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.14459","title":"Filling in the Mechanisms: How do LMs Learn Filler-Gap Dependencies under Developmental Constraints?","created":"2026-04-15","cited_by_count":0,"area":null},{"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":"2604.22166","title":"Fine-Grained Analysis of Shared Syntactic Mechanisms in Language Models","created":"2026-04-24","cited_by_count":0,"area":"mechinterp"},{"id":"2606.16407","title":"A Mechanistic Understanding of Pronoun Fidelity in LLMs","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.22428","title":"Unboxing Diffusion Models for the Arts: Interactive Model Bending and Practice-Based Explainability","created":"2026-07-24","cited_by_count":0,"area":"diffusion"},{"id":"2608.30662","title":"MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines","created":"2026-08-31","cited_by_count":0,"area":"mechinterp"},{"id":"2609.00443","title":"(V)LMs generalize beyond surface co-occurrence: Evidence from cross-modal number agreement","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.01356","title":"Separating Syntax from Language: A Mechanistic Account of Translation in Multilingual LLMs","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.04967","title":"One Token Can Be Enough: Bridging Prompting and Activation Steering with Prefix Steering","created":"2026-10-04","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}