© 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. 31513
    Prev
    Next
    INDEX
    Explanations

    key statistics related to sports performance

    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
    .scalablytyped
    -0.07
     sil
    -0.07
    DEVICE
    -0.07
    è¨ŃåĤĻ
    -0.07
     Bene
    -0.07
    æĿIJ
    -0.07
    .addObserver
    -0.07
    resh
    -0.06
    head
    -0.06
     foreign
    -0.06
    POSITIVE LOGITS
     late
    0.07
    bench
    0.06
    803
    0.06
    ayd
    0.06
     quarter
    0.06
     scoreboard
    0.06
    odo
    0.06
    atori
    0.06
    å°ļ
    0.06
    antal
    0.05
    Activations Density 0.059%

    No Known Activations