© 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. 15157
    Prev
    Next
    INDEX
    Explanations

    phrases indicating sources of information or justification for claims

    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
    ogan
    -0.06
    aci
    -0.06
    bas
    -0.06
    erras
    -0.06
    acÃŃ
    -0.06
    icago
    -0.06
    029
    -0.06
     Extensions
    -0.06
    avl
    -0.05
    umlu
    -0.05
    POSITIVE LOGITS
     Danger
    0.07
    /trunk
    0.07
    çī©
    0.07
    /******/
    0.07
    Ñĩива
    0.06
    ldb
    0.06
     кеÑĢ
    0.06
    ffe
    0.06
    (Func
    0.06
    kea
    0.06
    Activations Density 0.009%

    No Known Activations