© 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. 95080
    Prev
    Next
    INDEX
    Explanations

    names of artists and contributors in the art community

    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
    urum
    -0.07
    aurant
    -0.07
    esan
    -0.06
    competitive
    -0.06
    wap
    -0.06
    rance
    -0.06
     resultCode
    -0.06
    izzle
    -0.06
    conexao
    -0.06
    otlin
    -0.06
    POSITIVE LOGITS
    iminal
    0.07
    /maps
    0.07
    rips
    0.07
    .Void
    0.06
     GENERIC
    0.06
    -icons
    0.06
    ınca
    0.06
    ElementsBy
    0.06
    vak
    0.06
    OCUMENT
    0.06
    Activations Density 0.099%

    No Known Activations