© 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. 5291
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to infections and urinary system conditions

    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
    itzer
    -0.07
    ÃŃ
    -0.07
    orf
    -0.06
    erdale
    -0.06
    undry
    -0.06
    erse
    -0.06
    zá
    -0.06
     Franti
    -0.06
    fab
    -0.06
     Dash
    -0.06
    POSITIVE LOGITS
     vs
    0.11
     overview
    0.10
     Vs
    0.09
     explained
    0.09
    vs
    0.09
     ÚĨÛĮست
    0.09
    -definition
    0.08
     definition
    0.08
     facts
    0.08
    -vs
    0.08
    Activations Density 0.033%

    No Known Activations