About this paper
The best direction for probing a concept in a language model's hidden state is not the best direction for steering the model toward that concept, with implications for transfer and abstention.
A direction in a language model's hidden state can be used to probe whether a concept is present or to steer the model toward it. Although probe directions are often reused for steering, the direction that best detects a concept need not be the one that best changes it. We study this distinction in three instruction-tuned models from different families. We construct a one-parameter family of directions ranging from a covariance-adjusted discriminant to the mean difference, and evaluate probing and additive steering, which adds the direction to the hidden state, along the family at a fixed side effect. For truthfulness and sentiment, in every model, the best probe is not the best steering…
language model hidden stateprobe directionssteeringprobingadditive steeringcovariance-adjusted discriminantmean differenceinstruction-tuned modelslayer sweeprotation-based steering operator
- Upvotes
- 5
- Authors
- 2
- Published
- Nov 14, 2026
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
Trending history
Do Probing and Steering Favor the Same Directions Within and Across Language Models? was first seen on Hugging Face · Daily papers on Nov 21, 2026. Since then it has appeared in 5 checks on 1 different day. Its best position was #29 of 30, reached on Nov 21, 05:29 UTC. It dropped off the list after Nov 21, 13:29 UTC.