© 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. 104054
    Prev
    Next
    INDEX
    Explanations

    patterns related to programming concepts and behaviors in Python

    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
    Ž
    -0.07
    Require
    -0.06
     guest
    -0.06
     Sta
    -0.06
    天
    -0.06
     Blank
    -0.06
    odega
    -0.06
     League
    -0.06
     Zag
    -0.06
    emo
    -0.06
    POSITIVE LOGITS
    istrovstvÃŃ
    0.08
    028
    0.07
    339
    0.06
    448
    0.06
    Explanation
    0.06
    088
    0.06
    utow
    0.06
    338
    0.06
    tember
    0.06
     explanation
    0.06
    Activations Density 0.004%

    No Known Activations