© 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 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. 125607
    Prev
    Next
    INDEX
    Explanations

    references to prominent entities and events related to arts, medicine, and education

    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
     w
    -0.07
    aze
    -0.07
    igh
    -0.06
    _utilities
    -0.06
    AZE
    -0.06
     *,↵
    -0.06
    ấn
    -0.06
     trú
    -0.06
    ision
    -0.06
    ắc
    -0.06
    POSITIVE LOGITS
    raquo
    0.07
    olon
    0.07
    .htm
    0.06
    382
    0.06
    chner
    0.06
    ulfilled
    0.06
    .html
    0.06
     Maver
    0.06
     Uncategorized
    0.06
    inke
    0.06
    Activations Density 0.042%

    No Known Activations