© 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. 14117
    Prev
    Next
    INDEX
    Explanations

    numerical or quantifiable information, possibly related to dimensions or specifications

    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
    ÙĬÙĩ
    -0.07
    ght
    -0.07
    ilities
    -0.06
    ÏīÏĤ
    -0.06
    ennie
    -0.06
    ossal
    -0.06
    lein
    -0.06
    ruž
    -0.06
    gua
    -0.06
    UTH
    -0.06
    POSITIVE LOGITS
    chai
    0.07
    uchs
    0.06
     Eag
    0.06
    ewis
    0.06
     Mell
    0.06
     Core
    0.06
    /dat
    0.06
    dbuf
    0.06
     عدد
    0.06
    ãĥ¼ãĥľ
    0.06
    Activations Density 0.000%

    No Known Activations