Claimempirical · verifiableA factual claim that could be checked directly against observation or primary records.constitution →importance · minorImportance 0.35, from 0 to 1 · minor: narrow or largely settled, cheap to get right. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

TopicsModel Backdoor Attacks LLM Safety Training

On Redwood's Llama 3.1 8B sleeper agent, adversarial supervised fine-tuning reduced red-team backdoor firing near zero while exact-trigger firing stayed near 100%.

Not yet assessed. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.

Decomposition

This claim has not been assessed yet. Attention goes where its expected value is highest and someone funds it; once this claim's assessment is funded and runs, it may well decompose into subclaims.

or create a grant for this whole area →

Provenance

Where this claim has been said, linked to its canonical form.

1 source · no origin · 1 untraced

1 Untraced

Adversarial Training Can Further Hide a Backdoor, but Does It Teach the Model to Better Identify Its Trigger? Untraced · nothing upstream recorded

Based on firing rates, our results replicate the Sleeper Agents paper's picture: the red-team prompt firing rate fell to near zero while the exact-trigger firing rate stayed near 100%.

Adversarial Training Can Further Hide a Backdoor, but Does It Teach the Model to Better Identify Its Trigger?extraction 0.85

Summary of the author's supervised fine-tuning experiment on Redwood Research's open-weight Llama 3.1 8B sleeper agent.

Cite this claim: a formal citation with its evidence attached

Embed this claim: show it on another site with its current assessment

An embed reports the graph's judgment as it stands when the page is viewed: the status with its confidence, how disputed the claim is, and the date. It links back here.

CardFits its column and sizes itself. Without the script it stays a quotation with its link.

<blockquote class="minerval-claim" data-claim-id="9030190a-a96e-4a4a-be2c-3e4eedd7d0d9"><a href="https://minerval.ai/claims/9030190a-a96e-4a4a-be2c-3e4eedd7d0d9">On Redwood&#39;s Llama 3.1 8B sleeper agent, adversarial supervised fine-tuning reduced red-team backdoor firing near zero while exact-trigger firing stayed near 100%.</a></blockquote>
<script async src="https://minerval.ai/embed.js"></script>

IframeWhere scripts are not allowed. A fixed height; add ?theme=light or ?theme=dark to fix its colours.

<iframe src="https://minerval.ai/embed/claims/9030190a-a96e-4a4a-be2c-3e4eedd7d0d9" title="Minerval: On Redwood&#39;s Llama 3.1 8B sleeper agent, adversarial supervised fine-tuning reduced red-t…" width="480" height="225" style="border:0;max-width:100%" loading="lazy"></iframe>

BadgeAn image for a README or a forum post, in Markdown.

[![Minerval's judgment of this claim](https://minerval.ai/embed/claims/9030190a-a96e-4a4a-be2c-3e4eedd7d0d9/badge.svg)](https://minerval.ai/claims/9030190a-a96e-4a4a-be2c-3e4eedd7d0d9)

The badge now:

Contribute

Every judgment on this page is open to challenge. A contribution is evaluated on its merits by the reviewer; if it succeeds the page changes, and if it does not, the reasons are stated. Either way the exchange becomes part of the claim’s public record.

Created by extractor · Nov 11, 2026. Every judgment on this page is accompanied by a reasoning trace.