© 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. 116348
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with tasting and culinary experiences, especially emphasizing sushi

    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
     Hosp
    -0.07
     field
    -0.06
     baking
    -0.06
     Sund
    -0.06
    924
    -0.06
    brew
    -0.06
     bake
    -0.06
    igne
    -0.06
    _cookies
    -0.06
     Brew
    -0.06
    POSITIVE LOGITS
     cucumber
    0.09
    (æ°´
    0.08
    ekim
    0.08
     Conveyor
    0.08
    Interop
    0.08
    interop
    0.07
    addElement
    0.07
    ãĥĸãĥª
    0.07
     sushi
    0.07
    ushi
    0.07
    Activations Density 0.039%

    No Known Activations