© 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. 54443
    Prev
    Next
    INDEX
    Explanations

    import statements in programming code

    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
    bower
    -0.08
    üzel
    -0.08
    hower
    -0.07
    enton
    -0.06
    $_['
    -0.06
    [:,:
    -0.06
     sourceMappingURL
    -0.06
    ButtonModule
    -0.06
    ãĤīãģı
    -0.06
     côt
    -0.06
    POSITIVE LOGITS
     actionTypes
    0.06
     Technique
    0.06
    ynos
    0.06
    hab
    0.06
    sett
    0.06
    placer
    0.06
    998
    0.06
     technique
    0.06
    á»Ń
    0.06
    ÙĴس
    0.06
    Activations Density 0.001%

    No Known Activations