© 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. 94024
    Prev
    Next
    INDEX
    Explanations

    terminology related to immune responses and vaccination

    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
    buat
    -0.08
    ÌĨ
    -0.08
    eking
    -0.08
    icerca
    -0.07
    urette
    -0.07
    .getAs
    -0.07
    inka
    -0.07
    TOOLS
    -0.07
    .CopyTo
    -0.07
    ês
    -0.07
    POSITIVE LOGITS
     off
    0.06
    inston
    0.05
    rie
    0.05
    ãĥ»ãĤ¢
    0.05
     ç§
    0.05
    Closure
    0.05
    yon
    0.05
     å·Ŀ
    0.05
     diving
    0.05
    storm
    0.05
    Activations Density 0.003%

    No Known Activations