{"total":70,"rows":[{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2410.12877","title":"Improving Instruction-Following in Language Models through Activation Steering","created":"2024-10-15","cited_by_count":160,"area":"mechinterp"},{"id":"2411.02193","title":"Improving Steering Vectors by Targeting Sparse Autoencoder Features","created":"2024-11-04","cited_by_count":92,"area":"mechinterp"},{"id":"2502.02716","title":"A Unified Understanding and Evaluation of Steering Methods","created":"2025-02-04","cited_by_count":46,"area":"mechinterp"},{"id":"2504.14492","title":"FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering","created":"2025-04-20","cited_by_count":40,"area":"mechinterp"},{"id":"2406.17563","title":"Multi-property Steering of Large Language Models with Dynamic Activation Composition","created":"2024-06-25","cited_by_count":39,"area":"mechinterp"},{"id":"2410.16314","title":"Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering","created":"2024-10-09","cited_by_count":39,"area":"mechinterp"},{"id":"2501.09929","title":"Interpretable Steering of Large Language Models with Feature Guided Activation Additions","created":"2025-01-17","cited_by_count":35,"area":"mechinterp"},{"id":"2502.11356","title":"SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models","created":"2025-02-17","cited_by_count":34,"area":"mechinterp"},{"id":"2505.16188","title":"SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models","created":"2025-05-22","cited_by_count":29,"area":"mechinterp"},{"id":"2409.10053","title":"Householder Pseudo-Rotation: A Novel Approach to Activation Editing in LLMs with Direction-Magnitude Perspective","created":"2024-09-16","cited_by_count":23,"area":"mechinterp"},{"id":"2401.03735","title":"Language Models Encode the Value of Numbers Linearly","created":"2024-01-08","cited_by_count":20,"area":"mechinterp"},{"id":"2505.14352","title":"Towards eliciting latent knowledge from LLMs with mechanistic interpretability","created":"2025-05-20","cited_by_count":19,"area":"mechinterp"},{"id":"2503.10679","title":"LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss","created":"2025-03-11","cited_by_count":14,"area":"mechinterp"},{"id":"2502.14050","title":"Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder","created":"2025-02-19","cited_by_count":12,"area":"mechinterp"},{"id":"2510.10205","title":"PIXEL: Adaptive Steering Via Position-wise Injection with eXact Estimated Levels under Subspace Calibration","created":"2025-10-11","cited_by_count":11,"area":"mechinterp"},{"id":"2601.21900","title":"TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention","created":"2026-01-29","cited_by_count":11,"area":"mechinterp"},{"id":"2310.11476","title":"Program Translation via Code Distillation","created":"2023-10-17","cited_by_count":10,"area":"mechinterp"},{"id":"2512.22245","title":"Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation","created":"2025-12-23","cited_by_count":9,"area":"mechinterp"},{"id":"2501.11036","title":"LF-Steering: Latent Feature Activation Steering for Enhancing Semantic Consistency in Large Language Models","created":"2025-01-19","cited_by_count":8,"area":"mechinterp"},{"id":"2603.06745","title":"Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection","created":"2026-03-06","cited_by_count":6,"area":"mechinterp"},{"id":"2604.02608","title":"Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens","created":"2026-04-03","cited_by_count":6,"area":"mechinterp"},{"id":"2605.10664","title":"Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions","created":"2026-05-11","cited_by_count":6,"area":"mechinterp"},{"id":"2605.17231","title":"FishBack: Pullback Fisher Geometry for Optimal Activation Steering in Transformers","created":"2026-05-17","cited_by_count":6,"area":"mechinterp"},{"id":"2502.14133","title":"Self-Regularization with Sparse Autoencoders for Controllable LLM-based Classification","created":"2025-02-19","cited_by_count":5,"area":"mechinterp"},{"id":"2510.20479","title":"RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging","created":"2025-10-23","cited_by_count":5,"area":"mechinterp"},{"id":"2512.02004","title":"AlignSAE: Concept-Aligned Sparse Autoencoders","created":"2025-12-01","cited_by_count":4,"area":"mechinterp"},{"id":"2512.07667","title":"Depth-Wise Activation Steering for Honest Language Models","created":"2025-12-08","cited_by_count":4,"area":"mechinterp"},{"id":"2603.23301","title":"Steering LLMs for Culturally Localized Generation","created":"2026-03-24","cited_by_count":4,"area":"mechinterp"},{"id":"2606.22357","title":"ORBIT: Training-Free Multi-Attribute Behavioral Steering via Orthogonal Subspace Rotation","created":"2026-06-21","cited_by_count":4,"area":"mechinterp"},{"id":"2506.13727","title":"Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs","created":"2025-06-16","cited_by_count":3,"area":"mechinterp"},{"id":"2606.02628","title":"Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs","created":"2026-05-30","cited_by_count":3,"area":"mechinterp"},{"id":"2408.12834","title":"CLLMFS: A Contrastive Learning enhanced Large Language Model Framework for Few-Shot Named Entity Recognition","created":"2024-08-23","cited_by_count":2,"area":"mechinterp"},{"id":"2505.00624","title":"FineScope : SAE-guided Data Selection Enables Domain Specific LLM Pruning and Finetuning","created":"2025-05-01","cited_by_count":2,"area":"mechinterp"},{"id":"2505.03368","title":"Geospatial Mechanistic Interpretability of Large Language Models","created":"2025-05-06","cited_by_count":2,"area":"mechinterp"},{"id":"2505.24859","title":"Beyond Multiple Choice: Evaluating Steering Vectors for Summarization","created":"2025-05-30","cited_by_count":2,"area":"mechinterp"},{"id":"2509.22739","title":"Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models","created":"2025-09-25","cited_by_count":2,"area":"mechinterp"},{"id":"2511.12832","title":"From Passive to Persuasive: Localized Activation Injection for Empathy and Negotiation","created":"2025-11-16","cited_by_count":2,"area":"mechinterp"},{"id":"2603.02908","title":"SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training","created":"2026-03-03","cited_by_count":2,"area":"mechinterp"},{"id":"2604.13694","title":"Weight Patching: Toward Source-Level Mechanistic Localization in LLMs","created":"2026-04-15","cited_by_count":2,"area":"mechinterp"},{"id":"2604.15488","title":"FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models","created":"2026-04-16","cited_by_count":2,"area":"mechinterp"},{"id":"2605.03217","title":"Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability","created":"2026-05-04","cited_by_count":2,"area":"mechinterp"},{"id":"2605.27354","title":"Guiding LLM Post-training Data Engineering with Model Internals from Sparse Autoencoders","created":"2026-05-26","cited_by_count":2,"area":"mechinterp"},{"id":"2312.16291","title":"Observable Propagation: Uncovering Feature Vectors in Transformers","created":"2023-12-26","cited_by_count":1,"area":"mechinterp"},{"id":"2411.12589","title":"ULTra: Unveiling Latent Token Interpretability in Transformer-Based Understanding and Segmentation","created":"2024-11-15","cited_by_count":1,"area":"mechinterp"},{"id":"2506.07691","title":"Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models","created":"2025-06-09","cited_by_count":1,"area":"mechinterp"},{"id":"2511.00029","title":"Feature-Guided SAE Steering for Refusal-Rate Control using Contrasting Prompts","created":"2025-10-26","cited_by_count":1,"area":"mechinterp"},{"id":"2601.08070","title":"Semantic Gravity Wells: Why Negative Constraints Backfire","created":"2026-01-12","cited_by_count":1,"area":"mechinterp"},{"id":"2605.28553","title":"Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations","created":"2026-05-27","cited_by_count":1,"area":"mechinterp"},{"id":"2606.07696","title":"Adversarial Robustness of Activation Steering in Large Language Models","created":"2026-06-05","cited_by_count":1,"area":"mechinterp"},{"id":"2606.15092","title":"High-Dimensional Random Projection for Activation Steering in Language Models","created":"2026-06-13","cited_by_count":1,"area":"mechinterp"},{"id":"2607.28906","title":"Token-Level Diagnosis of Sycophancy in LLMs with Attribution-Guided Steering","created":"2026-07-31","cited_by_count":1,"area":"mechinterp"},{"id":"2608.24988","title":"Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal","created":"2026-08-25","cited_by_count":1,"area":"mechinterp"},{"id":"2609.05575","title":"Capsule Lens: Locating and Tracking Concept Geometry in Model Representations","created":"2026-09-04","cited_by_count":1,"area":"mechinterp"},{"id":"2512.22293","title":"Learning from Negative Examples: Why Warning-Framed Training Data Teaches What It Warns Against","created":"2025-12-25","cited_by_count":0,"area":"mechinterp"},{"id":"2602.13567","title":"DistillLens: Symmetric Knowledge Distillation Through Logit Lens","created":"2026-02-14","cited_by_count":0,"area":"mechinterp"},{"id":"2604.26866","title":"MoRFI: Monotonic Sparse Autoencoder Feature Identification","created":"2026-04-29","cited_by_count":0,"area":"mechinterp"},{"id":"2605.07324","title":"Activation Differences Reveal Backdoors: A Comparison of SAE Architectures","created":"2026-05-08","cited_by_count":0,"area":"mechinterp"},{"id":"2605.08254","title":"HyperTransport: Amortized Conditioning of T2I Generative Models","created":"2026-05-07","cited_by_count":0,"area":"mechinterp"},{"id":"2605.11426","title":"A Mechanistic Investigation of Supervised Fine Tuning","created":"2026-05-12","cited_by_count":0,"area":"mechinterp"},{"id":"2605.15604","title":"VSPO: Vector-Steered Policy Optimization for Behavioral Control","created":"2026-05-15","cited_by_count":0,"area":"mechinterp"},{"id":"2606.06214","title":"Towards the Readability of LLM-Generated Codes through Multitask Representation Engineering","created":"2026-06-04","cited_by_count":0,"area":"mechinterp"},{"id":"2607.05615","title":"A Coin Flip Per Token: Bernoulli Sparse Steering of Large Language Models","created":"2026-07-06","cited_by_count":0,"area":"mechinterp"},{"id":"2608.04904","title":"Strengthening Target-Language Features: SAE-Based Steering for Multilingual Inference","created":"2026-08-05","cited_by_count":0,"area":"mechinterp"},{"id":"2608.22034","title":"Align, Unify, Suppress, Route: A Coherentist View of Transformer Computation","created":"2026-08-22","cited_by_count":0,"area":"mechinterp"},{"id":"2608.25354","title":"Escaping Low-Dimensional Overlap: Multi-Task Model Merging via High-Dimensional Sparse Disentanglement","created":"2026-08-26","cited_by_count":0,"area":"mechinterp"},{"id":"2609.25021","title":"\"As a Language Model...\": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It","created":"2026-08-09","cited_by_count":0,"area":"mechinterp"},{"id":"2609.30405","title":"Adaptive Multi-Value Control in LLMs via Causal Activation Steering","created":"2026-09-24","cited_by_count":0,"area":"mechinterp"},{"id":"2609.36813","title":"RESCUE: Repairing Language Model Errors to Sparse Circuits via Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"mechinterp"},{"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}