Cosine similarity between truth probes

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

• Cosine Similarity-Based Deception Detectionconcept0.837
  Detection mechanism computing cosine similarity between activation vectors and steering vectors to classify deception
• Cosine Similarity Measurementmethod0.831
  Used to measure alignment between DIM direction and cone basis vectors to assess overlap
• Cosine Similarity of Persona Vectorsconcept0.797
  Geometric measure used to track persona vector drift and stability across checkpoints
• Masked Cosine Similaritymethod0.797
  Cosine similarity between feature activations restricted to tokens where one of the features fires; used to identify feature splitting relationships
• The model converges to a more stable truth direction in middle-to-late layers, as evidenced by increasing cosine similarity between layer-wise probes.claim0.781
  Supported by the geometric transition visible in cosine similarity heatmaps for F0-F3.
• Pairwise Cosine Similarity Analysismethod0.781
  Used to quantify the semantic clustering of adjective-set embeddings across model families and conditions
• Cosine Similarity Ranking for Instruction Discoverymethod0.780
  Method to discover new reflection-inducing instructions by ranking candidate tokens by cosine similarity to steering vectors.
• Pairwise cosine similarities between Description, Narration, and Dialogue evil vectors are all below 0.5finding0.780
  Shows different elicitation strategies recover qualitatively distinct persona directions