© 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. 9-LLAMASCOPE-RES-131K
    11. 93956
    Prev
    Next
    INDEX
    Explanations

    different types of food, particularly meats and accompanying ingredients

    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
    allis
    -0.08
    iban
    -0.07
    ooter
    -0.07
    ekim
    -0.07
    pect
    -0.07
    enties
    -0.06
    estre
    -0.06
    rese
    -0.06
    ADF
    -0.06
    Ø·ÙĦ
    -0.06
    POSITIVE LOGITS
    _COMPILE
    0.07
    kaç
    0.07
    sun
    0.07
     Sunrise
    0.07
    ceipt
    0.06
     æĤ
    0.06
    _undo
    0.06
     sunrise
    0.06
     Masks
    0.06
     Silva
    0.06
    Activations Density 0.023%

    No Known Activations