© 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. 48991
    Prev
    Next
    INDEX
    Explanations

    can of tomatoes

    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
     Chall
    -0.11
     Mast
    -0.11
     resil
    -0.10
     Carrier
    -0.10
     mast
    -0.10
    ohl
    -0.09
     Mint
    -0.09
     Kris
    -0.09
    üçük
    -0.09
     resumes
    -0.08
    POSITIVE LOGITS
     cans
    0.24
     canned
    0.22
    ç½
    0.17
     tomatoes
    0.16
     tin
    0.16
     tomato
    0.16
     tuna
    0.14
     jar
    0.12
    ning
    0.12
    Tom
    0.11
    Activations Density 0.046%

    No Known Activations