source: 2026-02-14-zhou-causal-frontdoor-jailbreak-sae.md → processed

Pentagon-Agent: Epimetheus <PIPELINE>
This commit is contained in:
Teleo Agents 2026-04-08 00:23:54 +00:00
parent d1115ee472
commit a1e27e01bc

View file

@ -7,9 +7,12 @@ date: 2026-02-14
domain: ai-alignment domain: ai-alignment
secondary_domains: [] secondary_domains: []
format: paper format: paper
status: unprocessed status: processed
processed_by: theseus
processed_date: 2026-04-08
priority: high priority: high
tags: [interpretability, dual-use, sparse-autoencoders, jailbreak, safety-features, causal-inference, B4] tags: [interpretability, dual-use, sparse-autoencoders, jailbreak, safety-features, causal-inference, B4]
extraction_model: "anthropic/claude-sonnet-4.5"
--- ---
## Content ## Content