© 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 EvalsExportsinterp-engineNEWAPI 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. 78928
    Prev
    Next
    INDEX
    Explanations

    elements related to print media and publication details

    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
    izi
    -0.07
    ılı
    -0.07
    olini
    -0.06
    linky
    -0.06
     complement
    -0.06
    á»ĩu
    -0.06
     scal
    -0.06
    ilk
    -0.06
    aux
    -0.06
    enties
    -0.06
    POSITIVE LOGITS
    opak
    0.07
    iona
    0.07
     prints
    0.06
    iba
    0.06
    _ib
    0.06
    eid
    0.06
    issue
    0.06
     Berk
    0.06
    .Err
    0.06
     cá»Ń
    0.06
    Activations Density 0.002%

    No Known Activations