© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 52033
    Prev
    Next
    INDEX
    Explanations

    ingredients for soup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eggs
    -0.12
    anship
    -0.10
     sauces
    -0.10
     Vul
    -0.10
     shallow
    -0.10
     scrambled
    -0.10
     eggs
    -0.09
     Cage
    -0.09
     serialVersionUID
    -0.09
    cone
    -0.09
    POSITIVE LOGITS
     bouquet
    0.17
     bay
    0.16
     Soup
    0.14
     Bou
    0.14
     soup
    0.13
    bay
    0.13
     bou
    0.12
     æ¹
    0.11
     rou
    0.11
    pot
    0.11
    Activations Density 0.015%

    No Known Activations