framework
active
framework:dynamic-steeringDynamic Steering
Steering variants that adaptively modulate steering strength based on input context or token position, addressing when to steer
Neighborhood — ranked by edge-count
Papers (1)
paper
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).
- Proposed future direction: model dynamically adjusts steering strength based on internal uncertainty during inference
- A method for modifying model behavior by adding perturbation vectors to activations, used here to try to reduce eval awareness.
- Steering variant that rotates hidden states toward a target feature vector, addressing how to steer
- Novel method that applies intervention only when the model begins a new thinking step (at the \n\n delimiter) rather than at every token
- Causal intervention technique: edit NLA explanation, reconstruct via AR, use difference as steering vector to manipulate model behavior.
- Typical approach that adds a scaled steering vector to representations; the paper argues this is mismatched with actual representation geometry.
- Using interventions to guide model generation behavior, e.g., adding sentiment vectors at inference time