© 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. 61942
    Prev
    Next
    INDEX
    Explanations

    elements and objects within programming or game development contexts, particularly in relation to collision shapes and graphical user interface components

    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
    erli
    -0.08
    uld
    -0.07
     Intermediate
    -0.07
    /*č↵
    -0.07
    .toolbox
    -0.07
    estate
    -0.06
    577
    -0.06
    emen
    -0.06
    raft
    -0.06
    ossal
    -0.06
    POSITIVE LOGITS
    +xml
    0.07
    å¼ı
    0.06
     Jub
    0.06
    ushima
    0.06
    WithTitle
    0.06
     whose
    0.06
    styled
    0.06
     jub
    0.06
     WithEvents
    0.06
     jur
    0.06
    Activations Density 0.034%

    No Known Activations