© 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. 108125
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and healthcare processes

    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
    мовÑĸÑĢ
    -0.08
     siempre
    -0.07
    rouw
    -0.07
    itta
    -0.07
     hereby
    -0.07
    BOVE
    -0.07
    ære
    -0.07
     завжди
    -0.07
    ager
    -0.07
    .deserialize
    -0.07
    POSITIVE LOGITS
     simply
    0.12
     actually
    0.09
     may
    0.09
     even
    0.09
     merely
    0.08
     Simply
    0.08
     simplement
    0.08
    actually
    0.08
     sometimes
    0.07
     can
    0.07
    Activations Density 0.052%

    No Known Activations