{"total":59,"rows":[{"id":"2511.00617","title":"Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering","created":"2025-11-01","cited_by_count":29,"area":"mechinterp"},{"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":"2604.25783","title":"Subliminal Steering: Stronger Encoding of Hidden Signals","created":"2026-04-28","cited_by_count":14,"area":"mechinterp"},{"id":"2606.00995","title":"Subliminal Learning Is Steering Vector Distillation","created":"2026-05-31","cited_by_count":13,"area":"mechinterp"},{"id":"2510.03659","title":"Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders","created":"2025-10-04","cited_by_count":10,"area":"mechinterp"},{"id":"2511.21399","title":"Steering Awareness: Detecting Activation Steering from Within","created":"2025-11-26","cited_by_count":9,"area":"mechinterp"},{"id":"2602.06801","title":"On the Non-Identifiability of Steering Vectors in Large Language Models","created":"2026-02-06","cited_by_count":8,"area":"mechinterp"},{"id":"2602.14869","title":"Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution","created":"2026-02-16","cited_by_count":8,"area":"mechinterp"},{"id":"2604.09839","title":"Steered LLM Activations are Non-Surjective","created":"2026-04-10","cited_by_count":8,"area":"mechinterp"},{"id":"2603.21396","title":"Mechanisms of Introspective Awareness","created":"2026-03-22","cited_by_count":7,"area":"mechinterp"},{"id":"2604.24693","title":"Contextual Linear Activation Steering of Language Models","created":"2026-04-27","cited_by_count":7,"area":"mechinterp"},{"id":"2605.00842","title":"Understanding Emergent Misalignment via Feature Superposition Geometry","created":"2026-04-07","cited_by_count":7,"area":"mechinterp"},{"id":"2511.18284","title":"What Can We Actually Steer? A Multi-Behavior Study of Activation Control","created":"2025-11-23","cited_by_count":6,"area":"mechinterp"},{"id":"2601.05437","title":"Tracing Moral Foundations in Large Language Models","created":"2026-01-09","cited_by_count":6,"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":"2605.10664","title":"Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions","created":"2026-05-11","cited_by_count":6,"area":"mechinterp"},{"id":"2607.07003","title":"Dissociating the Internal Representations of Sycophancy in LLMs","created":"2026-07-08","cited_by_count":6,"area":"mechinterp"},{"id":"2602.15847","title":"Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models","created":"2026-01-23","cited_by_count":5,"area":"mechinterp"},{"id":"2603.13249","title":"Steering at the Source: Style Modulation Heads for Robust Persona Control","created":"2026-02-24","cited_by_count":5,"area":"mechinterp"},{"id":"2605.01167","title":"Minimizing Collateral Damage in Activation Steering","created":"2026-05-01","cited_by_count":5,"area":"mechinterp"},{"id":"2605.03907","title":"Steer Like the LLM: Activation Steering that Mimics Prompting","created":"2026-05-05","cited_by_count":5,"area":"mechinterp"},{"id":"2606.11386","title":"Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering","created":"2026-06-09","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":"2511.00230","title":"Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AI","created":"2025-10-31","cited_by_count":3,"area":"mechinterp"},{"id":"2604.13466","title":"Functional Emotions or Situational Contexts? A Discriminating Test from the Mythos Preview System Card","created":"2026-04-09","cited_by_count":3,"area":"mechinterp"},{"id":"2607.25270","title":"Where Steering Signals Come From: Activation Source Selection in Activation Steering","created":"2026-07-28","cited_by_count":3,"area":"mechinterp"},{"id":"2509.00691","title":"CE-Bench: Towards a Reliable Contrastive Evaluation Benchmark of Interpretability of Sparse Autoencoders","created":"2025-08-31","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":"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":"2606.08682","title":"Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation","created":"2026-06-07","cited_by_count":2,"area":"mechinterp"},{"id":"2606.26155","title":"Detecting and Controlling Sycophancy with Cascading Linear Features","created":"2026-06-23","cited_by_count":2,"area":"mechinterp"},{"id":"2608.08024","title":"Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States","created":"2026-08-08","cited_by_count":2,"area":"mechinterp"},{"id":"2608.11227","title":"Forecasting Side Effects of Activation Steering","created":"2026-07-28","cited_by_count":2,"area":"mechinterp"},{"id":"2603.22295","title":"Whether, Not Which: Mechanistic Interpretability Reveals Dissociable Affect Reception and Emotion Categorization in LLMs","created":"2026-03-15","cited_by_count":1,"area":"mechinterp"},{"id":"2605.05983","title":"Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions","created":"2026-05-07","cited_by_count":1,"area":"mechinterp"},{"id":"2605.16362","title":"When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search","created":"2026-05-09","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":"2606.28548","title":"Turn-Averaged SAEs for Feature Discovery and Long-Context Attribution","created":"2026-06-26","cited_by_count":1,"area":"mechinterp"},{"id":"2608.11025","title":"Data Attribution of Emergent Misalignment with Persona Features","created":"2026-08-11","cited_by_count":1,"area":"mechinterp"},{"id":"2609.07037","title":"Disentangling Steering Vectors","created":"2026-09-07","cited_by_count":1,"area":"mechinterp"},{"id":"2601.02978","title":"Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencoders","created":"2026-01-06","cited_by_count":0,"area":"mechinterp"},{"id":"2602.19157","title":"Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs","created":"2026-02-22","cited_by_count":0,"area":"mechinterp"},{"id":"2605.03160","title":"Steering grids for sparse-autoencoder features: when a top-context label names an activation regime rather than a causal axis","created":"2026-05-04","cited_by_count":0,"area":"mechinterp"},{"id":"2605.09773","title":"Exploitation Without Deception: Dark Triad Feature Steering Reveals Separable Antisocial Circuits in Language Models","created":"2026-05-10","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":"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":"2607.06845","title":"LLMs Silently Correct African American English: Auditing and Mitigating Dialect Bias via Activation Steering","created":"2026-07-07","cited_by_count":0,"area":"mechinterp"},{"id":"2607.20803","title":"The Geometry of Personality: Activation Steering with Jungian Cognitive Functions","created":"2026-07-23","cited_by_count":0,"area":"mechinterp"},{"id":"2608.02957","title":"Inverted Detection and Control in Steering Vectors","created":"2026-08-03","cited_by_count":0,"area":"mechinterp"},{"id":"2608.08383","title":"Safety Cost of Steering Vectors Is Separable and Reducible","created":"2026-08-09","cited_by_count":0,"area":"mechinterp"},{"id":"2608.29215","title":"Attribute-Based Activation Steering of LLMs for Group-Specific Explanation Generation","created":"2026-08-29","cited_by_count":0,"area":"mechinterp"},{"id":"2609.06951","title":"Steering Interference Reflects the Model's Defaults, Not the Behavior Directions","created":"2026-09-07","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":"2609.31122","title":"LocUS: Head Selection and Subspace Projection for Targeted Activation Steering","created":"2026-09-25","cited_by_count":0,"area":"mechinterp"},{"id":"2609.36388","title":"Persona Dosing: Calibrated Activation Steering for Graded Trait Control","created":"2026-09-28","cited_by_count":0,"area":"mechinterp"},{"id":"2610.05794","title":"A Testable Theory of Atomic Features","created":"2026-10-05","cited_by_count":0,"area":"mechinterp"},{"id":"2610.14025","title":"Contrastive Covariance Subspaces for Activation Steering","created":"2026-09-29","cited_by_count":0,"area":"mechinterp"},{"id":"2610.19114","title":"Genesis Steering: Better Activation Steering Through Training Data","created":"2026-10-13","cited_by_count":0,"area":"mechinterp"},{"id":"2610.19359","title":"Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering","created":"2026-10-14","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}