© 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. 74478
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions

    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
    ắn
    -0.08
     MÃľ
    -0.07
    ibbon
    -0.07
    âĢ¢↵↵
    -0.07
    AZY
    -0.07
     tvá
    -0.07
     ãģĿãģ®ä»ĸ
    -0.07
    urette
    -0.07
    ovna
    -0.07
     Ulus
    -0.07
    POSITIVE LOGITS
     second
    0.08
    ;
    0.07
    á
    0.06
    ann
    0.06
     (
    0.06
     [
    0.06
     {
    0.06
     Secondly
    0.06
     ii
    0.06
    ses
    0.06
    Activations Density 0.020%

    No Known Activations