{"total":17,"rows":[{"id":"2604.02029","title":"The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook","created":"2026-04-02","cited_by_count":43,"area":null},{"id":"2501.08319","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions","created":"2025-01-14","cited_by_count":41,"area":null},{"id":"2412.19512","title":"Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging","created":"2024-12-27","cited_by_count":11,"area":null},{"id":"2507.23220","title":"Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders","created":"2025-07-31","cited_by_count":8,"area":null},{"id":"2602.04735","title":"From Data to Behavior: Predicting Unintended Model Behaviors Before Training","created":"2026-02-04","cited_by_count":8,"area":null},{"id":"2502.16385","title":"Toward a Flexible Framework for Linear Representation Hypothesis Using Maximum Likelihood Estimation","created":"2025-02-22","cited_by_count":3,"area":null},{"id":"2602.04903","title":"Mind the Performance Gap: Capability-Behavior Trade-offs in Feature Steering","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2603.18329","title":"FaithSteer-BENCH: A Deployment-Aligned Stress-Testing Benchmark for Inference-Time Steering","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2605.08326","title":"LLM Advertisement based on Neuron Auctions","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2604.06263","title":"Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2605.20262","title":"Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.27199","title":"Forecasting With LLMs: Improved Generalization Through Feature Steering","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2608.18093","title":"Abliteration Mitigation via Refusal Aliases","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2609.22153","title":"SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.22224","title":"From Trait Vectors to Circuits: Tracing Refusal and Sycophancy Through Language Models","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.32457","title":"Write Back the $\\Delta$: Revisiting the Same Tokens with Fresh Representations","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.39701","title":"Values as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM Steering","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}