© 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. 123594
    Prev
    Next
    INDEX
    Explanations

    syntax-related characters and structures in programming code

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     ä¹ĭ
    -0.07
    luet
    -0.07
    stup
    -0.07
    serter
    -0.07
    رÙħ
    -0.06
    егоÑĢ
    -0.06
    ---</
    -0.06
    ----</
    -0.06
    γη
    -0.06
    اÙĬا
    -0.06
    POSITIVE LOGITS
     finally
    0.10
     Lastly
    0.10
    Lastly
    0.09
     Finally
    0.09
    finally
    0.08
    Finally
    0.08
     final
    0.07
    erken
    0.06
    ités
    0.06
    :last
    0.06
    Activations Density 0.027%

    No Known Activations