Sweep Less, Steer More: Using Activation Steering Geometry for Reduced Hyperparameter Search
cs.LG, cs.AI, cs.CL
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- Representation Engineering for Large-Language Models: Survey and Research Challenges
- Signatures of Steerability in Activation Space of Language Models
- Predicting Where Steering Vectors Succeed
- Understanding Unreliability of Steering Vectors in Language Models: Geometric Predictors and the Limits of Linear Approximations
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- When is Your LLM Steerable?
- Gemma 2: Improving Open Language Models at a Practical Size
- The Llama 3 Herd of Models
- Steering Language Models With Activation Engineering
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis