© 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. 94844
    Prev
    Next
    INDEX
    Explanations

    web navigation elements and content indicators

    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
     Blanch
    -0.07
    idor
    -0.07
    ohn
    -0.06
    FD
    -0.06
    zem
    -0.06
    endar
    -0.06
    uar
    -0.06
     Bern
    -0.06
    zing
    -0.06
    erd
    -0.05
    POSITIVE LOGITS
    arih
    0.08
    annes
    0.07
    urance
    0.07
    öl
    0.07
    ancel
    0.07
    auté
    0.06
    enant
    0.06
    APS
    0.06
    TypeID
    0.06
    icode
    0.06
    Activations Density 0.001%

    No Known Activations