© 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. 27059
    Prev
    Next
    INDEX
    Explanations

    sections or identifiers in a document or dataset

    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
    927
    -0.07
    ÐĽÐĺ
    -0.07
    posium
    -0.07
    cheid
    -0.06
    chy
    -0.06
    ROUT
    -0.06
    ZO
    -0.06
    hoe
    -0.06
    erd
    -0.06
    uco
    -0.06
    POSITIVE LOGITS
    inç
    0.07
     Clayton
    0.06
     exercise
    0.06
    \views
    0.06
    .scalablytyped
    0.06
     drying
    0.06
     Gap
    0.06
     æĿ¡
    0.06
    earer
    0.06
    (section
    0.06
    Activations Density 0.008%

    No Known Activations