© 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. 69787
    Prev
    Next
    INDEX
    Explanations

    clinical terminology related to patient medical history and treatment

    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
     Marker
    -0.07
     or
    -0.07
     ifs
    -0.07
     Kund
    -0.06
    awan
    -0.06
    sts
    -0.06
    Indicator
    -0.06
    cents
    -0.06
    isme
    -0.06
    409
    -0.06
    POSITIVE LOGITS
    zar
    0.07
    اعÙĬ
    0.06
     left
    0.06
    ืà¹ī
    0.06
    .tim
    0.06
    Keywords
    0.06
    ‘s
    0.06
     Harrison
    0.06
    idar
    0.06
     dernier
    0.06
    Activations Density 0.040%

    No Known Activations