Less Sycophancy, Stronger Refusal? Lessons for AI Safety from Mechanistic Interpretability

arXiv:2609.35544 · cs.CL, cs.AI, cs.LG · Submitted 2026-09-28 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/Xu0615/Sycophancy_Safety_via_SAE

Terminology

• Sycophancy — 128× in this paper · explained in 4 episodes
• Steering — 27× in this paper · explained in 2 episodes
• Fine-Tuning — 12× in this paper · explained in 5 episodes
• Alignment — 5× in this paper · explained in 1 episode
• Interpretability — 5× in this paper · explained in 15 episodes
• Activation Addition — 3× in this paper · explained in 1 episode
• Ablation — 2× in this paper · explained in 1 episode
• Generalization — 2× in this paper · explained in 13 episodes
• Representation Engineering — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• BatchTopK Sparse Autoencoders
• Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
• Persona Vectors: Monitoring and Controlling Character Traits in Language Models
• Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models
• Decoupled Weight Decay Regularization
• Steering Language Models With Activation Engineering
• Simple synthetic data reduces sycophancy in large language models
• Representation Engineering: A Top-Down Approach to AI Transparency

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering