LocUS: Head Selection and Subspace Projection for Targeted Activation Steering

arXiv:2609.31122 · cs.CL, cs.LG · Submitted 2026-09-25 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• Steering — 82× in this paper · explained in 2 episodes
• Sycophancy — 20× in this paper · explained in 4 episodes
• Calibration — 10× in this paper · explained in 7 episodes
• Transformer — 9× in this paper · explained in 2 episodes
• Activation Steering — 8× in this paper · explained in 4 episodes
• Accuracy — 7× in this paper · explained in 1 episode
• Alignment — 4× in this paper · explained in 1 episode
• Interpretability — 4× in this paper · explained in 15 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• In International Conference on Learning Representations — 3× in this paper
• Activation Addition — 2× in this paper · explained in 1 episode
• Catastrophic Forgetting — 2× in this paper · explained in 5 episodes
• Linear probe — 2× in this paper · explained in 2 episodes
• Meeting of the Association for Computational Linguistics — 2× in this paper
• Perplexity — 2× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• International Conference on Machine Learning — 1× in this paper
• LLM judge — 1× in this paper · explained in 2 episodes
• Reconstruction Error — 1× in this paper · explained in 2 episodes
• Representation Engineering — 1× in this paper · explained in 2 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes

Sources

• DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
• Persona Vectors: Monitoring and Controlling Character Traits in Language Models
• The Llama 3 Herd of Models
• Steering at the Source: Style Modulation Heads for Robust Persona Control
• Mistral 7B
• An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning
• DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
• Steering Language Models With Activation Engineering
• 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