© 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. 123421
    Prev
    Next
    INDEX
    Explanations

    symbols and syntax related to programming or mathematical expressions

    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
    (æĹ¥
    -0.10
    anford
    -0.09
    vál
    -0.08
    (æ°´
    -0.08
    esome
    -0.08
     ìļ´ìĺģìŀIJ
    -0.08
    &eacute
    -0.08
    _OBJC
    -0.08
    ÑĢавилÑĮ
    -0.07
    icontrol
    -0.07
    POSITIVE LOGITS
    âĢ¦↵
    0.06
    Âłin
    0.06
    istrator
    0.06
    /vendors
    0.05
     âĢ¦↵
    0.05
     [âĢ¦]↵
    0.05
    /Admin
    0.05
     whom
    0.05
    sha
    0.05
    337
    0.05
    Activations Density 0.120%

    No Known Activations