© 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 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. 126562
    Prev
    Next
    INDEX
    Explanations

    JavaScript function definitions and structural code 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
    const
    -0.07
    pray
    -0.06
    atsby
    -0.06
    izzo
    -0.06
     certain
    -0.06
     const
    -0.06
     Canter
    -0.06
     int
    -0.06
     Hen
    -0.05
     Gould
    -0.05
    POSITIVE LOGITS
    ekim
    0.08
    .prototype
    0.08
    ViewById
    0.07
    리카
    0.07
    ungan
    0.07
    -syntax
    0.07
    947
    0.07
    berman
    0.06
    اÙĨÙĩ
    0.06
    vÄĽt
    0.06
    Activations Density 0.013%

    No Known Activations