method
active
method:ocean-trait-covariance-matrix-mOCEAN Trait Covariance Matrix M
5x5 Pearson correlation matrix of OCEAN traits computed from MDS injection sweeps to assess cross-trait leakage
Neighborhood — ranked by edge-count
Concepts (1)
concept
- Cross-Trait LeakageimplementsUnintended movement of non-target OCEAN traits when steering toward a target trait; quantified via lambda metric
Claims (1)
claim
- Interpretive conclusion from Big Two mismatch finding; tentative due to only 46.15% match rate
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.
- Primary personality model used to benchmark steering methods across 14 LLMs
- Testing five phrasings of the self-referential prompt to confirm robustness to wording variation
- Named procedure for classifying each trait by baseline expression and dose-response under steering
- Novel aggregation technique replacing mean pooling; preserves joint activation structure (feature co-occurrence) in token embeddings.
- Five variants of the experimental prompt tested to confirm the effect is robust to changes in specific wording
- Dominant dimensional framework in personality psychology used to ground the OCEAN traits in the generic domain inventory
- The geometric relationships among Big Five trait steering vectors in activation space, found to be preserved across architectures
- Mechanistic finding explaining why high-N personas are safe under steering