© 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. 78405
    Prev
    Next
    INDEX
    Explanations

    references to items or collections in a context that indicates a listing or inventory

    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
    allee
    -0.07
    /manual
    -0.07
    iones
    -0.06
    ionic
    -0.06
    laps
    -0.06
    otec
    -0.06
     nomine
    -0.06
    assium
    -0.06
    roke
    -0.06
    )))));↵
    -0.06
    POSITIVE LOGITS
    hist
    0.06
    utting
    0.06
    haul
    0.06
    ovan
    0.06
    atti
    0.06
    ouz
    0.06
    nore
    0.06
    ORMAT
    0.06
    esser
    0.06
    adden
    0.06
    Activations Density 0.001%

    No Known Activations