concept
active
concept:control-vectors-cvsControl Vectors (CVs)
Attribute-aligned shifts added to the residual stream to steer LLM generation toward desired personality traits
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- The primary novel framework introduced in the paper for learning facet-level personality control vectors
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- A method for modifying model behavior by adding perturbation vectors to activations, used here to try to reduce eval awareness.
- Vectors acquired during pretraining in Backpack LMs that have a multiplication effect on model generation
- Prior framework for monitoring and controlling character traits in LLMs via activation directions; this paper extends it to 275 roles
- Linear representations of emotion concepts extracted from activations.
- Used to extract trait and style directions.
- Translates steering vector via weighted average of shared decoder vectors.
- Steering vector extracted in Experiment 2 capturing latent representation of desired role behavior and honesty semantics