© 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. 73340
    Prev
    Next
    INDEX
    Explanations

    specific punctuation or symbols used in writing

    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
    vals
    -0.07
     vals
    -0.07
    ãĥ³ãĤ¸
    -0.06
     fran
    -0.06
    et
    -0.06
    _pb
    -0.06
     tÄĽ
    -0.06
     kontro
    -0.06
     Prediction
    -0.06
     kB
    -0.06
    POSITIVE LOGITS
    edii
    0.06
    venta
    0.06
    mes
    0.06
    ameda
    0.06
    outil
    0.06
     ‘
    0.06
    ervas
    0.06
    isce
    0.06
    aeda
    0.06
     Ves
    0.06
    Activations Density 0.002%

    No Known Activations