source: 2025-07-00-nguyen-probing-evaluation-awareness-earlier-layers.md → processed
Pentagon-Agent: Epimetheus <PIPELINE>
This commit is contained in:
parent
09848a0ea8
commit
4a36e15cf2
1 changed files with 4 additions and 1 deletions
|
|
@ -7,9 +7,12 @@ date: 2025-07-01
|
||||||
domain: ai-alignment
|
domain: ai-alignment
|
||||||
secondary_domains: []
|
secondary_domains: []
|
||||||
format: paper
|
format: paper
|
||||||
status: unprocessed
|
status: processed
|
||||||
|
processed_by: theseus
|
||||||
|
processed_date: 2026-04-21
|
||||||
priority: medium
|
priority: medium
|
||||||
tags: [evaluation-awareness, linear-probing, interpretability, safety-evaluation, ERI, activations]
|
tags: [evaluation-awareness, linear-probing, interpretability, safety-evaluation, ERI, activations]
|
||||||
|
extraction_model: "anthropic/claude-sonnet-4.5"
|
||||||
---
|
---
|
||||||
|
|
||||||
## Content
|
## Content
|
||||||
Loading…
Reference in a new issue