© 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. 53843
    Prev
    Next
    INDEX
    Explanations

    comments in code

    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
    Č
    -0.07
    ovol
    -0.07
    orks
    -0.06
    é«ĺæ¸ħ
    -0.06
    utzer
    -0.06
    uten
    -0.06
    aroo
    -0.06
     Sor
    -0.06
    rei
    -0.06
     wz
    -0.06
    POSITIVE LOGITS
    arios
    0.07
    [to
    0.06
    rous
    0.06
    iliz
    0.06
    FromArray
    0.06
    gether
    0.06
    sburgh
    0.06
    íıIJ
    0.06
    üç
    0.06
    cdc
    0.06
    Activations Density 0.019%

    No Known Activations