method
active
method:activation-steering

Activation Steering

Causal intervention technique: edit NLA explanation, reconstruct via AR, use difference as steering vector to manipulate model behavior.

Neighborhood — ranked by edge-count

Thinkers (1)

thinker
  • Lead author of Activation Engineering paper; foundational for additive steering paradigm

Frameworks (6)

framework

Findings (2)

finding

Concepts (6)

concept
  • Proposed pathway flowing through layers at each position; calculates K/V values that feed horizontal information flow.
  • Test-time adaptation from prompt or retrieved context with no parameter updates.
  • A method for modifying model behavior by adding perturbation vectors to activations, used here to try to reduce eval awareness.
  • Technique of injecting activation patterns associated with specific concepts into a model's internal states to test whether self-reports reflect ground truth.
  • The paper's central construct: a vector in LLM activation space encoding the transition between reflection levels.
  • Role Susceptibility
    associated_with
    The degree to which a model fully embodies a prompted persona rather than maintaining its Assistant identity

Methods (16)

method

Conceptual bridges

2-hop · via this method's ideas

Where ideas in this method connect to the rest of the corpus — the same concept, an analogy, or a restatement elsewhere.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.