© 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. 80049
    Prev
    Next
    INDEX
    Explanations

    quantifiable metrics or numerical values

    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
     fewer
    -0.06
    869
    -0.06
     amongst
    -0.06
    ourg
    -0.06
    etimes
    -0.06
    olem
    -0.06
    assen
    -0.06
    æ¶
    -0.06
    lays
    -0.06
    __,__
    -0.06
    POSITIVE LOGITS
    ean
    0.08
    fold
    0.08
    ÑĢÑĸÑĩ
    0.07
    .promise
    0.07
    yah
    0.06
    Porno
    0.06
    arus
    0.06
    istringstream
    0.06
     Editors
    0.06
    bsub
    0.06
    Activations Density 0.031%

    No Known Activations