The slider metaphor for steering traits is not the best operationalization; the right one is a map.

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

• The slider metaphor for persona vectors is not the best operationalization; the right one is a mapclaim0.854
  The paper argues that framing persona vectors as uniform dials misses the layered structure of natural/steerable/intractable regimes
• Optimally steering model behavior requires isolating concept geometry and defining operators to navigate it.claim0.805
• Slider metaphor for persona vectorsconcept0.799
  The framing of persona vectors as dials that can be uniformly turned up or down; the paper argues this is an insufficient operationalization
• Steering preferentially amplifies exaggerated and undesirable styles, not competence-oriented or assistant-default behaviorsclaim0.775
  The top of the steerability ranking is dominated by exaggerated or attention-grabbing styles
• Steering base models along the assistant axis extracted from instruct models promotes helpful human archetypes and agreeable traits, suggesting the axis predates post-trainingfinding0.773
  Validation finding from Lu et al. 2026 supporting PSM's claim about pre-training persona structure
• Steering's effect on verbalized chain-of-thought evaluation/deployment beliefs is a useful proxy for its effect on actual deployment behaviorclaim0.772
  Practical guidance for practitioners who lack ground-truth model organisms.
• Steering along manifolds provides better control than linear steering when the concept geometry is non-linear.claim0.769
  The central thesis of the paper, motivating the shift from linear to geometry-aware manifold steering.
• Linear steering is often mismatched with a model's internal representation geometry, producing noisy, off-target effects.claim0.768
  The paper's critique of the standard linear steering baseline, supported by the days-of-week demo.