© 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. 60982
    Prev
    Next
    INDEX
    Explanations

    references to templates or structured formats

    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
    onya
    -0.06
     DF
    -0.06
    irth
    -0.06
    ones
    -0.06
     concern
    -0.06
    nan
    -0.06
    reak
    -0.05
    urgery
    -0.05
    itches
    -0.05
    uci
    -0.05
    POSITIVE LOGITS
    #End
    0.07
     bomb
    0.07
    edd
    0.07
    phem
    0.07
    clud
    0.07
    ATAB
    0.07
    alom
    0.07
    ÑĨеп
    0.07
    Std
    0.07
    Uvs
    0.07
    Activations Density 0.000%

    No Known Activations