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

    Neuronpedia

    Jacobian LensNEW
    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. 85302
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns and personal names

    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
    çģ
    -0.06
    inium
    -0.06
    andum
    -0.06
    flo
    -0.06
    èįī
    -0.06
    inia
    -0.06
     Gund
    -0.06
     dar
    -0.06
    anio
    -0.06
    anas
    -0.06
    POSITIVE LOGITS
    izzle
    0.08
    ibli
    0.07
    ÙĨاÙħ
    0.07
    ibName
    0.07
    ade
    0.07
    yal
    0.07
    SetName
    0.07
    .getSimpleName
    0.07
    ãĥ³ãĥij
    0.07
     SimpleName
    0.06
    Activations Density 0.006%

    No Known Activations