© 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. 63274
    Prev
    Next
    INDEX
    Explanations

    key aspects of collaboration and community involvement in arts and media

    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
    æĮĻ
    -0.06
    avir
    -0.06
    Uploaded
    -0.06
    apolis
    -0.06
     Posted
    -0.06
    ddb
    -0.06
    IRTUAL
    -0.06
    irc
    -0.06
    Å®
    -0.06
    à¹īาà¸ĩ
    -0.06
    POSITIVE LOGITS
     magazine
    0.13
     editorial
    0.10
     editor
    0.10
     paper
    0.10
     Magazine
    0.10
    azine
    0.09
     magazines
    0.09
    editor
    0.09
     editors
    0.09
     column
    0.09
    Activations Density 0.011%

    No Known Activations