Feature Elicitation for SAE Steering of Deceptive Behaviour in Small LLMs
arXiv 2610.20638v1•ccbdec48a2e73b1d59ad85ba6253e45a74f760e9051f9c9ff7f59c2a10370c6a
Paper metadata
- arXiv ID
- 2610.20638
- Version
- v1
- Category
- cs.CY, cs.LG
- Authors
- J Koorndijk
- Publication date
- 2026-10-16T04:00:00Z
- Source identifier
- 2610.20638v1
- Public record ID
- record:sha256:ccbdec48a2e73b1d59ad85ba6253e45a74f760e9051f9c9ff7f59c2a10370c6a
The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.
This is source-provided metadata, not an enriched summary or an impact assessment. Follow the canonical source link for the published material.
Evidence and limitations
- Source ID
- arxiv_research
- Record identifier
- ccbdec48a2e73b1d59ad85ba6253e45a74f760e9051f9c9ff7f59c2a10370c6a
- Record type
- Source metadata
This record may overlap with other records. Source metadata can be incomplete or change. Validate consequential decisions against the linked source and your own environment.