© 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. 15-LLAMASCOPE-RES-131K
    11. 88706
    Prev
    Next
    INDEX
    Explanations

    HTML comments and code relevant to web development

    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
     accom
    -0.06
     Ker
    -0.06
    mite
    -0.06
    .='
    -0.06
    üt
    -0.06
     ker
    -0.06
    /commons
    -0.06
    ysa
    -0.06
    anyl
    -0.06
    bjerg
    -0.06
    POSITIVE LOGITS
    deen
    0.08
    avin
    0.07
    \Twig
    0.07
    canf
    0.06
    zej
    0.06
    zyst
    0.06
    enna
    0.06
    ếu
    0.06
    enk
    0.06
    ฤ
    0.06
    Activations Density 0.001%

    No Known Activations