© 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. 63226
    Prev
    Next
    INDEX
    Explanations

    discussions related to healthcare access and intellectual property issues during the pandemic

    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
    loff
    -0.07
    ãĥ¯ãĤ¤ãĥĪ
    -0.07
     Barrel
    -0.07
    Carthy
    -0.07
    RSS
    -0.07
    .Formatter
    -0.07
    ë´IJ
    -0.07
    ãĤ¤ãĥĦ
    -0.07
    ENU
    -0.07
    Checksum
    -0.07
    POSITIVE LOGITS
     respir
    0.07
     Cuomo
    0.07
     ventil
    0.07
    amic
    0.07
    uet
    0.06
     respiratory
    0.06
     shortages
    0.06
     spikes
    0.06
     Testing
    0.06
     virus
    0.06
    Activations Density 0.070%

    No Known Activations