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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 119939
    Prev
    Next
    INDEX
    Explanations

    academic and research-related concepts, particularly those related to pathology and clinical studies

    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
    ooter
    -0.06
    ophone
    -0.06
    CMP
    -0.06
    merce
    -0.06
     EOF
    -0.06
    ĨĴ
    -0.06
    Admin
    -0.05
    سÙĥ
    -0.05
     client
    -0.05
    Authority
    -0.05
    POSITIVE LOGITS
     nos
    0.08
    ATS
    0.07
     Schwartz
    0.07
    /editor
    0.07
    queda
    0.07
    (Abstract
    0.07
    Editor
    0.07
    BJECT
    0.06
    ritt
    0.06
    orman
    0.06
    Activations Density 0.126%

    No Known Activations