© 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. 41737
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulations and oversight in facilities and organizations

    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
     migrationBuilder
    -0.07
    incinn
    -0.07
     Folk
    -0.07
    pcl
    -0.07
    tuk
    -0.07
    ewe
    -0.07
    _blocking
    -0.06
    tah
    -0.06
    rk
    -0.06
     Fol
    -0.06
    POSITIVE LOGITS
     meiden
    0.07
    written
    0.07
     Written
    0.07
     written
    0.07
    ade
    0.06
    Written
    0.06
    /documentation
    0.06
     mÃŃt
    0.06
    èĩ³å°ij
    0.06
    Ïģθ
    0.06
    Activations Density 0.001%

    No Known Activations