© 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. 54404
    Prev
    Next
    INDEX
    Explanations

    terms related to data generation and analysis in healthcare or scientific contexts

    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
    ú
    -0.05
     Nurs
    -0.05
     KD
    -0.05
    E
    -0.05
     Bren
    -0.05
    ç«ĭãģ¦
    -0.05
    ÙĦÙĪ
    -0.05
    uer
    -0.05
    apro
    -0.05
    thin
    -0.05
    POSITIVE LOGITS
    glich
    0.07
    zek
    0.07
    acente
    0.07
    enské
    0.07
    лиÑĨ
    0.07
    684
    0.07
    tÃŃ
    0.07
    iliz
    0.07
    stdClass
    0.07
    .literal
    0.07
    Activations Density 0.309%

    No Known Activations