© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126803
    Prev
    Next
    INDEX
    Explanations

    words related to biomedical and clinical research

    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
    ãĥ¼ãĥ¬
    -0.07
    _FAR
    -0.06
    mani
    -0.06
    istorical
    -0.06
     -*-č↵
    -0.06
    HONE
    -0.06
     äºĨ
    -0.06
    صت
    -0.06
    Ìģc
    -0.06
    quit
    -0.06
    POSITIVE LOGITS
    arters
    0.07
    umo
    0.06
     Studies
    0.06
    uous
    0.06
    ushima
    0.06
    amage
    0.06
    -testid
    0.06
    354
    0.06
     (“
    0.06
     Coast
    0.06
    Activations Density 0.006%

    No Known Activations