© 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. 121650
    Prev
    Next
    INDEX
    Explanations

    references to academic books and publications

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Insecta
    -0.07
    yar
    -0.07
    pter
    -0.07
    olini
    -0.07
    ìĦ¤
    -0.06
     Ø¢ÙĦ
    -0.06
    خاص
    -0.06
     AVC
    -0.06
     Convention
    -0.06
    continued
    -0.06
    POSITIVE LOGITS
     The
    0.07
    ency
    0.07
    (Editor
    0.06
    (ed
    0.06
     book
    0.06
     Beyond
    0.06
     SOLD
    0.06
     ãĢĬ
    0.06
    isel
    0.06
    tring
    0.06
    Activations Density 0.052%

    No Known Activations