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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31300
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their various occurrences in the text

    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
    eree
    -0.06
     snapchat
    -0.06
    fb
    -0.06
     fault
    -0.06
     Wick
    -0.06
    FB
    -0.06
    Translated
    -0.06
     https
    -0.06
     DependencyProperty
    -0.06
     instagram
    -0.05
    POSITIVE LOGITS
    obuf
    0.07
    ems
    0.07
    :"-"`↵
    0.07
    .echo
    0.06
    poz
    0.06
     ìı
    0.06
    717
    0.06
    vre
    0.06
    ejs
    0.06
    dfd
    0.06
    Activations Density 0.018%

    No Known Activations