© 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. 15116
    Prev
    Next
    INDEX
    Explanations

    headings and section titles in a document

    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
    ses
    -0.07
     Leh
    -0.07
    ing
    -0.07
     Gro
    -0.06
    et
    -0.06
    (Editor
    -0.06
    atta
    -0.06
     rein
    -0.06
     Canter
    -0.06
     Cousins
    -0.06
    POSITIVE LOGITS
     جستارÙĩاÛĮ
    0.09
    #[
    0.09
     ê°ĻìĿ´
    0.08
     Appendix
    0.08
    yntax
    0.07
     âĹĨ
    0.07
     destinationViewController
    0.07
    tright
    0.07
    uze
    0.07
    vette
    0.07
    Activations Density 0.003%

    No Known Activations