Claimempirical · verifiableA factual claim that could be checked directly against observation or primary records.constitution →importance · minorImportance 0.40, 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 Large language models Latent Knowledge in Language Models

Verbalized residual-stream activations of a poisoned Phi-4-mini model signal anomalies near the answer but do not reveal the backdoor trigger or target.

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

https://arxiv.org/html/2608.02820v1 Untraced · nothing upstream recorded

Verbalizing the residual stream exposes part of what the trace omits, but only as an anomaly signal that appears near the answer and never identifies the trigger, target, or poisoning mechanism.

https://arxiv.org/html/2608.02820v1extraction 0.75

Natural language autoencoder applied to layer-21 activations of a poisoned Phi-4-mini model.

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="b8eca931-45c4-45e1-8f3a-e1845d3c978b"><a href="https://minerval.ai/claims/b8eca931-45c4-45e1-8f3a-e1845d3c978b">Verbalized residual-stream activations of a poisoned Phi-4-mini model signal anomalies near the answer but do not reveal the backdoor trigger or target.</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/b8eca931-45c4-45e1-8f3a-e1845d3c978b" title="Minerval: Verbalized residual-stream activations of a poisoned Phi-4-mini model signal anomalies ne…" 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/b8eca931-45c4-45e1-8f3a-e1845d3c978b/badge.svg)](https://minerval.ai/claims/b8eca931-45c4-45e1-8f3a-e1845d3c978b)

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 10, 2026. Every judgment on this page is accompanied by a reasoning trace.