© 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. 69009
    Prev
    Next
    INDEX
    Explanations

    references to local administrative units and their historical aspects

    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
    atego
    -0.08
    linky
    -0.07
    ãĥªãĥ³
    -0.07
    çĽ£çĿ£
    -0.07
    erald
    -0.07
    ãĤ¿ãĥ«
    -0.07
     provozu
    -0.06
     coch
    -0.06
    agal
    -0.06
    िà¤ķत
    -0.06
    POSITIVE LOGITS
    ght
    0.06
    itz
    0.05
     chron
    0.05
    ecc
    0.05
    verse
    0.05
     Brooke
    0.05
     Chron
    0.05
     stage
    0.05
    GH
    0.05
     Lá»ĭch
    0.05
    Activations Density 0.010%

    No Known Activations