© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 120025
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements and punctuation

    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
    .habbo
    -0.06
     Kil
    -0.06
     Harding
    -0.06
     Grund
    -0.06
    ril
    -0.06
    uppy
    -0.06
    ving
    -0.06
    se
    -0.06
     Hill
    -0.06
     dela
    -0.06
    POSITIVE LOGITS
    ãĥ³ãĥĩãĤ£
    0.08
    _ads
    0.07
    longleftrightarrow
    0.07
    .shtml
    0.06
    efault
    0.06
     {/*
    0.06
     âĹĦ
    0.06
    خص
    0.06
     @}
    0.06
     UNU
    0.06
    Activations Density 0.015%

    No Known Activations