Single neuron steering works far worse than contrastive-pair control vectors in practice
burny_tech · x · 2026-10-28
Developer lumpenspace reports from hands-on experience that single neuron steering, like SAEs before it, performs far worse than contrastive-pair control vectors in practice, judging by coherence and consistency of model outputs. A practical data point for anyone working on model behavior steering.
More from Research
- UltraVBERT: a 247M-parameter vision-language encoder for visual document retrieval — kalyan_kpl · 2026-10-28
- Anders Sandberg on a wild 48 hours: group classification formalized, Kakeya, RCE, AI incident — anderssandberg · 2026-10-28
- EvidenceConnect boosts multimodal perception without zooming, sweeping 8 benchmarks — inclusionAI · 2026-10-28
- What 200 years of philology reveals about LLM confabulation's structural root — vasilisvj · 2026-10-28
- Map-based localization hits 1.9cm RMSE across EuRoC flights in visloc-rs — rsasaki0109 · 2026-10-28
- BeeNara v0.4: 332MB local doc sorter hits 91.5% on unseen folders — razer_psycho · 2026-10-28