© 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. 53749
    Prev
    Next
    INDEX
    Explanations

    numerical data and dates

    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
    iri
    -0.07
    γοÏģ
    -0.06
    ircles
    -0.06
    entine
    -0.06
    ifs
    -0.06
    ongs
    -0.06
    xls
    -0.06
    osaurs
    -0.06
    uids
    -0.06
    urdy
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.07
     Sanayi
    0.07
     fal
    0.06
    ç©į
    0.06
    SOLE
    0.06
    CEED
    0.06
    mando
    0.06
     ThÃłnh
    0.06
     ull
    0.06
     slun
    0.06
    Activations Density 0.003%

    No Known Activations