© 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. 9-LLAMASCOPE-RES-131K
    11. 99246
    Prev
    Next
    INDEX
    Explanations

    dates and references to time

    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
    led
    -0.06
    imest
    -0.06
    hurst
    -0.06
     gere
    -0.06
    orp
    -0.06
    [
    -0.06
    ãĥ³ãĤº
    -0.06
    uid
    -0.06
    aug
    -0.06
    393
    -0.06
    POSITIVE LOGITS
    íĥĪ
    0.07
    udu
    0.07
    ÑĮогоднÑĸ
    0.07
    obus
    0.07
    èĸ¦
    0.07
    .metro
    0.07
    oteca
    0.06
    uden
    0.06
    #ad
    0.06
    .opend
    0.06
    Activations Density 0.003%

    No Known Activations