© 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. 42728
    Prev
    Next
    INDEX
    Explanations

    collective actions and inclusivity

    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
    ÏĥÏĦÏĮ
    -0.07
    olson
    -0.07
    öm
    -0.07
    eparator
    -0.07
    neider
    -0.07
    ngo
    -0.07
    estro
    -0.06
    lint
    -0.06
    ä¼Ļ
    -0.06
    ushing
    -0.06
    POSITIVE LOGITS
     comm
    0.06
    idot
    0.06
     fall
    0.06
     pageTitle
    0.06
     Visitors
    0.06
     cá»Ļng
    0.06
     kans
    0.06
    ural
    0.06
    ео
    0.06
    iod
    0.06
    Activations Density 0.001%

    No Known Activations