© 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. 69014
    Prev
    Next
    INDEX
    Explanations

    activities related to community engagement and spiritual practices

    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
    .ua
    -0.08
    fern
    -0.08
    uga
    -0.07
    ifo
    -0.07
     Period
    -0.07
    urum
    -0.07
    angan
    -0.07
    adian
    -0.07
    period
    -0.07
    ucch
    -0.07
    POSITIVE LOGITS
     every
    0.08
     twice
    0.07
     weekly
    0.07
    ç¯
    0.07
     attendance
    0.06
     æij
    0.06
     initially
    0.06
     Every
    0.06
     week
    0.06
     eb
    0.06
    Activations Density 0.037%

    No Known Activations