© 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. 81537
    Prev
    Next
    INDEX
    Explanations

    commands and inquiries regarding information sharing

    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
    foon
    -0.07
    ilot
    -0.07
    ecko
    -0.07
     Hüs
    -0.07
    ÃĹ↵↵
    -0.07
    /Foundation
    -0.07
    steder
    -0.07
    _ADAPTER
    -0.07
    hausen
    -0.07
    eday
    -0.07
    POSITIVE LOGITS
    stile
    0.06
    g
    0.06
    788
    0.06
    ByPrimaryKey
    0.06
    ODE
    0.06
    irection
    0.06
     engines
    0.06
    spring
    0.06
    kses
    0.06
    INARY
    0.05
    Activations Density 0.008%

    No Known Activations