© 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. 40491
    Prev
    Next
    INDEX
    Explanations

    references to specific medical or drug-related topics

    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
    ãģ£ãģı
    -0.07
    âĢ¦"↵↵
    -0.07
    ¶Į
    -0.07
    ANGLE
    -0.06
    882
    -0.06
    úng
    -0.06
    Ìģt
    -0.06
     Busty
    -0.06
    iao
    -0.06
    ÏĦζ
    -0.06
    POSITIVE LOGITS
    auen
    0.08
    doch
    0.07
    ruba
    0.07
     Uncategorized
    0.07
     numberWith
    0.07
    plode
    0.07
    ForObject
    0.06
    tright
    0.06
    indered
    0.06
    ucose
    0.06
    Activations Density 0.000%

    No Known Activations