© 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. 21620
    Prev
    Next
    INDEX
    Explanations

    cinnamon, ginger, cumin, spices

    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
     succ
    -0.11
     commod
    -0.10
    enta
    -0.10
     salty
    -0.10
     sor
    -0.09
     bucket
    -0.09
     Gan
    -0.09
     cran
    -0.09
    succ
    -0.09
     Olive
    -0.09
    POSITIVE LOGITS
     cinnamon
    0.29
     ginger
    0.24
    innamon
    0.23
     Ginger
    0.22
     spice
    0.22
     cloves
    0.21
     card
    0.20
     Spice
    0.19
     Clo
    0.18
     spices
    0.17
    Activations Density 0.064%

    No Known Activations