© 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. 28100
    Prev
    Next
    INDEX
    Explanations

    references to official statements or announcements regarding allegations and decisions

    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
     IRepository
    -0.06
    ulerAngles
    -0.06
     Tooth
    -0.06
    à¸Ńà¸ļ
    -0.06
     Sold
    -0.05
     Shoot
    -0.05
    maal
    -0.05
     pauses
    -0.05
    Thought
    -0.05
     Thought
    -0.05
    POSITIVE LOGITS
    iou
    0.08
    ourd
    0.07
    izzo
    0.07
    kü
    0.07
    aget
    0.07
    loff
    0.07
    icode
    0.07
    ëĿ½
    0.07
     Friday
    0.07
     {{↵
    0.07
    Activations Density 0.014%

    No Known Activations