© 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. 17938
    Prev
    Next
    INDEX
    Explanations

    code and programming language constructs related to event handling and callbacks

    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
    uell
    -0.09
    ulong
    -0.07
    _flutter
    -0.07
    /Peak
    -0.07
    raci
    -0.07
    amina
    -0.07
    buie
    -0.07
    ÅĤa
    -0.07
    خت
    -0.07
    /cop
    -0.07
    POSITIVE LOGITS
    venes
    0.07
     arity
    0.06
     Neb
    0.06
    å¼ı
    0.06
     Rat
    0.06
    .identity
    0.06
     Lou
    0.05
    REFERRED
    0.05
     rat
    0.05
    929
    0.05
    Activations Density 0.032%

    No Known Activations