© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 104207
    Prev
    Next
    INDEX
    Explanations

    keywords related to organizational structures and governance

    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
    çķĻ
    -0.07
    acho
    -0.07
    /the
    -0.07
    izza
    -0.06
    itness
    -0.06
    jun
    -0.06
    èµı
    -0.06
    emmel
    -0.06
    ieres
    -0.06
    ÑĢаÑģÑĤ
    -0.06
    POSITIVE LOGITS
     members
    0.06
    (s
    0.06
     member
    0.06
     Watts
    0.06
    762
    0.06
    ubl
    0.06
     interchangeable
    0.06
    =cut
    0.06
     bodies
    0.06
    à¸ļà¸Ĺ
    0.06
    Activations Density 0.031%

    No Known Activations