© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2944
    Prev
    Next
    INDEX
    Explanations

    control flow and state-related commands in programming or coding contexts

    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
    _hpp
    -0.07
    asley
    -0.07
    .habbo
    -0.07
     haus
    -0.07
    ÑĩаÑĤ
    -0.07
    ÑĸÑĩна
    -0.07
    ỡ
    -0.07
    iliz
    -0.07
    ÄŁ
    -0.07
    Ìģt
    -0.07
    POSITIVE LOGITS
     //
    0.11
    //
    0.10
    <!--
    0.09
     <!--
    0.08
     -
    0.08
     {/*
    0.07
    eton
    0.06
     #
    0.06
     /*
    0.06
    endon
    0.06
    Activations Density 0.056%

    No Known Activations