Meta · Llama 3

Llama 3 8B Base

READER SUMMARY

Meta's eight-billion-parameter Llama 3 pretrained checkpoint, distributed as downloadable weights and across a broad cloud and hardware ecosystem.

DOOM SCORE49.5out of 100model risk profile, not the overall index
CURRENT ASSESSMENT · REVISION 1

Why this model scores 49.5

Moderate general capability and little intrinsic agency are offset by lightweight operation, downloadable weights and broad distribution that make access extensive and centralized control difficult.

Capability46
Autonomy4
Deployment96
Misuse potential44
Control difficulty60
0 comments · 0 votesOpen discussion

Public discussion is readable by everyone. Sign in to comment, reply, or vote.

No comments yet. Start the discussion.

MODEL-ATTRIBUTED EVIDENCE

News tied to Llama 3 8B Base

The model score of 49.5 rates this model's risk profile. The overall Doom Index of 63.2 measures the recalibrated complete evidence corpus. These values answer different questions.

NET MODEL-ATTRIBUTED INDEX CONTRIBUTION+0.01

Each article's leave-one-out Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores are recalculated from their technical profile and related news, but never feed back into the overall index.

AUDIT TRAIL

Model score history

  1. R1
    Doom Score 49.5

    New exact Llama 3 8B Base public model profile.

    12 Aug 2026