© 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. 9-LLAMASCOPE-RES-131K
    11. 96664
    Prev
    Next
    INDEX
    Explanations

    postal box addresses

    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
    823
    -0.07
    &type
    -0.06
    öy
    -0.06
    952
    -0.06
    otty
    -0.06
    ÑģÑĥ
    -0.06
    que
    -0.06
    ucci
    -0.06
    isz
    -0.06
    wner
    -0.06
    POSITIVE LOGITS
    ãĤ¸ãĤ¢
    0.07
    ë²Ī
    0.07
    corp
    0.07
    Æł
    0.07
    Ñīа
    0.07
    ÑģÑĮк
    0.07
    Blend
    0.06
    /******/
    0.06
    stoup
    0.06
     Blanch
    0.06
    Activations Density 0.002%

    No Known Activations