why does SAE-based CV injection preserve general dialogue coherence while CAA can destabilize it?

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

• CV-SAE provides a more concentrated 'purer' steering direction with less extraneous content than CV-CAA, enabling higher FA without rising MTRclaim0.799
  Author's interpretation of why SAE outperforms CAA in stability at higher injection strengths
• The combined CV-SAE+Prompt configuration achieves the best overall performance, confirming that contrastively trained latent vectors enhance persona control while preserving dialogue coherenceclaim0.763
  Central performance claim of the paper summarizing experimental results
• We hypothesize that the control signal learned by CV-CAA is less 'pure' than CV-SAE; as α increases, off-target semantic components are introduced alongside the intended concept directionhypothesis0.760
  Mechanistic hypothesis explaining differential stability between SAE and CAA methods
• CV methods were resilient and often improved under contextualized questions; CV-SAE+Prompt gained +7.5pp FA on Qwen3-4Bfinding0.739
  Demonstrates that latent steering generalizes better to situational cues than prompt-only methods
• Mid-range α values with CV-SAE deliver high FA and low errors, while CV-CAA peaks at smaller α and shows faster MTR growthfinding0.739
  Characterizes the differential sensitivity to injection strength between SAE and CAA methods
• Both CV-SAE and CV-CAA substantially outperform Prompt-Label baseline across FA, MSE, and MAE on both backbonesfinding0.727
  Confirms effectiveness of direct vector modulation over prompt-only conditioning
• As α increases in CV-CAA, off-target semantic components are introduced alongside the intended concept direction, degrading response quality and inflating MTRclaim0.715
  Author's mechanistic explanation for CV-CAA instability at higher injection strengths
• CV-SAE achieves 7.0% MTR on Mistral-7B abstract questions vs 29.1% for CV-CAAfinding0.709
  Demonstrates that SAE-based injection is substantially more stable than CAA on Mistral-7B