© 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. 116624
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes related to web content structure

    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
    ifu
    -0.06
    ihan
    -0.06
    orsk
    -0.06
     much
    -0.06
    hec
    -0.06
    ALCHEMY
    -0.06
    áo
    -0.06
    ients
    -0.06
    obe
    -0.06
    ãĤīãĤĮãģ¦
    -0.06
    POSITIVE LOGITS
     Äijiá»ĥn
    0.07
     oppon
    0.07
    ¢åįķ
    0.06
     #__
    0.06
    onis
    0.06
    ouser
    0.06
    .|
    0.06
     ssize
    0.06
    arehouse
    0.06
    erten
    0.06
    Activations Density 0.013%

    No Known Activations