© 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. 74935
    Prev
    Next
    INDEX
    Explanations

    terms related to governance and organization

    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
    _marshall
    -0.07
    \Blueprint
    -0.07
    wich
    -0.07
    ecko
    -0.07
    .GroupLayout
    -0.07
    /WebAPI
    -0.07
    anium
    -0.07
     pÅĻÃŃpadnÄĽ
    -0.07
    orc
    -0.07
    .twimg
    -0.07
    POSITIVE LOGITS
     Ñģобой
    0.12
    çļĦæĺ¯
    0.10
     ÑģобоÑİ
    0.09
    :↵
    0.07
    ovit
    0.06
    erra
    0.06
    :
    0.06
     respectively
    0.06
    ned
    0.06
    ment
    0.06
    Activations Density 0.077%

    No Known Activations