© 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. 116721
    Prev
    Next
    INDEX
    Explanations

    numeric identifiers and associated cataloging information

    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
    ometr
    -0.07
    нÑĸв
    -0.07
    олоÑģ
    -0.07
    _TP
    -0.07
    ä¿
    -0.07
    .cv
    -0.07
    icens
    -0.07
    uo
    -0.06
    åį·
    -0.06
    artz
    -0.06
    POSITIVE LOGITS
    utes
    0.07
    odash
    0.07
    -alist
    0.07
    _dash
    0.06
    (#)
    0.06
    (s
    0.06
    Ã¶ÃŁe
    0.06
    dash
    0.06
    sage
    0.06
    izen
    0.06
    Activations Density 0.017%

    No Known Activations