© 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. 42324
    Prev
    Next
    INDEX
    Explanations

    references to antibiotic treatment in medical literature

    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
     MyApp
    -0.06
    ½Ķ
    -0.06
    kus
    -0.06
    chein
    -0.06
     Levy
    -0.06
    bedo
    -0.06
     cade
    -0.06
     census
    -0.06
     station
    -0.06
     Weiner
    -0.06
    POSITIVE LOGITS
     meta
    0.17
    meta
    0.16
     Meta
    0.16
    Meta
    0.15
    .meta
    0.14
    /meta
    0.13
    -meta
    0.13
    META
    0.13
    _meta
    0.12
     META
    0.12
    Activations Density 0.127%

    No Known Activations