© 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. 78492
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to various topics

    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
    âĺĨ
    -0.07
    raž
    -0.07
    aq
    -0.06
    azes
    -0.06
    eyen
    -0.06
    agas
    -0.06
    aña
    -0.06
    outu
    -0.06
    ascar
    -0.06
    nÄĽ
    -0.06
    POSITIVE LOGITS
     ÛĮعÙĨÛĮ
    0.10
     ($.
    0.10
    nam
    0.10
     namely
    0.09
     yani
    0.08
    ìĿ¸
    0.08
     (~
    0.07
     ($
    0.07
    582
    0.07
    Nam
    0.07
    Activations Density 0.286%

    No Known Activations