Refusal direction

Arditi et al. 2024 finding that refusal behavior is mediated by one direction in LLM activations; exemplar of single-direction causal results

Neighborhood — ranked by edge-count

paper

concept

Refusal Direction in LLMs
related_to
Prior finding that LLM refusal is mediated by a single latent direction, analogous to this paper's reflection direction.

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.

Truth Directionconcept0.811
A hypothesized direction in LLM activation space that encodes the truth or falsehood of factual statements
refusal rateconcept0.798
The percentage of harmful requests that a model refuses to answer, a common safety metric.
Reflection directionconcept0.778
A direction in the model's representation space that governs self-reflection behavior, computed as mean difference between reflection and non-reflection embeddings
Trait Refusal Alignment Frameworkframework0.775
A geometric framework relating Big Five trait steering vector alignment with the refusal direction to predict activation-steering safety vulnerability on a per-model basis
direction-based steeringconcept0.773
Paradigm of finding the right direction in activation space (e.g., linear steering).
Refusal Vectorconcept0.770
Single linear direction mediating refusal behavior in LLMs, shown by Arditi et al.; related to but distinct from the Assistant Axis
Goal-Directednessconcept0.763
Proposed universal invariant of cognition and intelligence—capacity for goal-directed activity in a problem space, independent of substrate or embodiment.
Chain-of-thought refusal mechanismconcept0.759
Residual refusals after evil-vector transfer originate inside the model's chain-of-thought, not at input or decode level