© 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. 15-LLAMASCOPE-RES-131K
    11. 85980
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure elements, particularly related to plotting and graphical representations

    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
     terminal
    -0.06
     unre
    -0.06
    itech
    -0.06
    compileComponents
    -0.05
    bottom
    -0.05
    кÑĤа
    -0.05
    terminal
    -0.05
    -terminal
    -0.05
    xcd
    -0.05
    kol
    -0.05
    POSITIVE LOGITS
    eyn
    0.07
    ÄĽtÃŃ
    0.07
     Kurd
    0.07
    ëĿ¼ëıĦ
    0.07
     [--
    0.07
    ynes
    0.06
    éĦ
    0.06
    \Helpers
    0.06
    elib
    0.06
    неÑģ
    0.06
    Activations Density 0.018%

    No Known Activations