method
active
method:steering-based-exclusivity-scoreSteering-based exclusivity score
Transfer-based 1-5 score via model stitching and LLM judge; 6 minus similarity.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (2)
method
- Causal intervention technique: edit NLA explanation, reconstruct via AR, use difference as steering vector to manipulate model behavior.
- Model StitchingusesTechnique to measure representational compatibility by integrating intermediate representations of one model into another
Artifacts (1)
artifact
- Claude 4.1 OpususesLLM judge and explainer used throughout.
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.
- Paradigm of finding the right direction in activation space (e.g., linear steering).
- The central phenomenon introduced by this paper: inference-time recovery from irrelevant activation steering in LLMs
- Paradigm of finding the right geometry (manifold) for principled control.
- Named procedure for simultaneously injecting two persona vectors and measuring joint trait-expression outcomes
- Steering toward directions that deviate from the model's typical generation distribution, causing rapid coherency collapse
- Add scaled steering vector to layer activations.
- Modifying model behavior by clamping SAE feature activations to specific values during forward pass.
- Best SJT steering score for a given method, instrument, layer, stride, trait, and direction combination; the primary comparison metric