© 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. 42779
    Prev
    Next
    INDEX
    Explanations

    items or components related to food and recipes

    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
    ','');↵
    -0.08
    ERP
    -0.08
     ï¼ľ
    -0.08
     zev
    -0.08
    ãĥĢãĤ¤
    -0.08
     wiÄĻc
    -0.07
    .datas
    -0.07
    å±ĭ
    -0.07
     karak
    -0.07
    ứng
    -0.07
    POSITIVE LOGITS
     etc
    0.14
    etc
    0.09
    antro
    0.07
    /or
    0.07
     gloss
    0.06
    Question
    0.06
    uez
    0.06
     aka
    0.06
    yntaxException
    0.05
    otime
    0.05
    Activations Density 0.038%

    No Known Activations