© 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. 93839
    Prev
    Next
    INDEX
    Explanations

    discussions about personal artistic expression and exhibition settings

    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
     recording
    -0.06
    ansk
    -0.06
    ANI
    -0.06
     updateTime
    -0.06
     Bid
    -0.06
    .tool
    -0.06
    иденÑĤ
    -0.06
    skyt
    -0.06
     suspicious
    -0.06
     Recording
    -0.06
    POSITIVE LOGITS
     display
    0.07
    Minimal
    0.07
     space
    0.07
     ấn
    0.07
    inspace
    0.07
    ulan
    0.07
    _hooks
    0.07
    lington
    0.07
     jur
    0.07
    -display
    0.07
    Activations Density 0.025%

    No Known Activations