© 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. 1671
    Prev
    Next
    INDEX
    Explanations

    programming-related identifiers and variables

    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
    nger
    -0.09
    TOOLS
    -0.08
    stantiate
    -0.08
    aju
    -0.07
    TEGER
    -0.07
    ALSE
    -0.07
    iyon
    -0.07
    ëĶĶìĭľ
    -0.07
    ยà¸ĩ
    -0.07
    icerca
    -0.07
    POSITIVE LOGITS
    scription
    0.07
    ried
    0.07
    wards
    0.06
    i
    0.06
    spar
    0.06
    ÛĮ
    0.06
    abella
    0.06
    elsius
    0.06
     ì²
    0.06
    MeasureSpec
    0.06
    Activations Density 0.056%

    No Known Activations