© 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. 4500
    Prev
    Next
    INDEX
    Explanations

    terms related to medical studies and treatment outcomes

    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
    .React
    -0.07
    afc
    -0.07
    ãĥ¼ãĥ³
    -0.07
    Diagnostic
    -0.07
    ãĤ
    -0.07
    emme
    -0.07
    taire
    -0.06
    ocab
    -0.06
    linger
    -0.06
    ilk
    -0.06
    POSITIVE LOGITS
     Study
    0.07
     Nobel
    0.07
    ONT
    0.07
     trial
    0.06
     study
    0.06
    онÑĤ
    0.06
     heart
    0.06
    Study
    0.06
    trial
    0.06
     Random
    0.06
    Activations Density 0.003%

    No Known Activations