© 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. 72679
    Prev
    Next
    INDEX
    Explanations

    references to specific years

    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
    اصÙĦ
    -0.07
    iffe
    -0.07
    znám
    -0.07
    296
    -0.07
    tries
    -0.07
    umen
    -0.07
    ówn
    -0.07
    .Override
    -0.06
     Prim
    -0.06
    285
    -0.06
    POSITIVE LOGITS
    st
    0.07
    agma
    0.06
     Cursors
    0.06
    ellen
    0.06
     ÙħÛĮÙĦادÛĮ
    0.06
    repo
    0.06
    inka
    0.06
    rea
    0.06
    EXTERN
    0.06
     curs
    0.06
    Activations Density 0.199%

    No Known Activations