© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 77656
    Prev
    Next
    INDEX
    Explanations

    comments and annotations related to code or script sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acades
    -0.06
    .quality
    -0.06
     Carn
    -0.06
     Mor
    -0.06
     Dro
    -0.06
     Dirt
    -0.06
    736
    -0.06
    visor
    -0.06
    witter
    -0.06
     Flat
    -0.06
    POSITIVE LOGITS
     END
    0.12
     endregion
    0.12
     end
    0.11
    endregion
    0.11
     ends
    0.11
    .END
    0.10
    ç»ĵæĿŁ
    0.10
    END
    0.10
     ended
    0.10
     End
    0.10
    Activations Density 0.008%

    No Known Activations