diff --git a/inbox/queue/2026-02-14-zhou-causal-frontdoor-jailbreak-sae.md b/inbox/archive/ai-alignment/2026-02-14-zhou-causal-frontdoor-jailbreak-sae.md similarity index 97% rename from inbox/queue/2026-02-14-zhou-causal-frontdoor-jailbreak-sae.md rename to inbox/archive/ai-alignment/2026-02-14-zhou-causal-frontdoor-jailbreak-sae.md index c0b732e31..51e044b57 100644 --- a/inbox/queue/2026-02-14-zhou-causal-frontdoor-jailbreak-sae.md +++ b/inbox/archive/ai-alignment/2026-02-14-zhou-causal-frontdoor-jailbreak-sae.md @@ -7,9 +7,12 @@ date: 2026-02-14 domain: ai-alignment secondary_domains: [] format: paper -status: unprocessed +status: processed +processed_by: theseus +processed_date: 2026-04-08 priority: high tags: [interpretability, dual-use, sparse-autoencoders, jailbreak, safety-features, causal-inference, B4] +extraction_model: "anthropic/claude-sonnet-4.5" --- ## Content