© 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. 38202
    Prev
    Next
    INDEX
    Explanations

    terms related to Google Analytics

    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
    .Align
    -0.06
    iek
    -0.06
    à¸Ńà¹Ģม
    -0.06
     perk
    -0.06
    odo
    -0.06
    azor
    -0.06
    ãĥĨãĤ£
    -0.06
    ixer
    -0.06
     Palmer
    -0.06
    کات
    -0.06
    POSITIVE LOGITS
    trak
    0.07
    -scalable
    0.07
     SCALE
    0.07
    جÙĪ
    0.07
    JS
    0.06
    opensource
    0.06
    mdb
    0.06
    mdl
    0.06
    aroo
    0.06
    uda
    0.06
    Activations Density 0.001%

    No Known Activations