© 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. 70276
    Prev
    Next
    INDEX
    Explanations

    technical specifications and operational details of advanced machinery and systems

    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
     âĨĴ↵↵
    -0.07
    aign
    -0.07
     Decompiled
    -0.07
    /archive
    -0.06
    ifes
    -0.06
     jub
    -0.06
     åı
    -0.06
    /*č↵
    -0.06
     Sentry
    -0.06
    ASI
    -0.06
    POSITIVE LOGITS
    currently
    0.08
     currently
    0.07
    enegro
    0.07
    currentColor
    0.06
    subject
    0.06
    edium
    0.06
    esser
    0.06
    witter
    0.06
    456
    0.06
    assel
    0.06
    Activations Density 0.046%

    No Known Activations