© 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. 108912
    Prev
    Next
    INDEX
    Explanations

    references to the concept of time and frequency

    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
    adil
    -0.07
    allet
    -0.07
    cul
    -0.06
    oshi
    -0.06
    away
    -0.06
    echa
    -0.06
    è¨Ģ
    -0.06
    .Helper
    -0.06
    CTL
    -0.06
    ouser
    -0.06
    POSITIVE LOGITS
     consecutive
    0.08
     dur
    0.07
    unctuation
    0.06
     encore
    0.06
    iggs
    0.06
    ÑħÑĥ
    0.06
    dera
    0.06
     again
    0.06
     Friedman
    0.06
    islation
    0.06
    Activations Density 0.006%

    No Known Activations