© 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. 21423
    Prev
    Next
    INDEX
    Explanations

    tomato

    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
     pec
    -0.11
    ãĥ«ãĤ¯
    -0.10
     bark
    -0.10
    YRO
    -0.10
     ÐļÑĢи
    -0.10
     nut
    -0.10
     Lars
    -0.10
    nuts
    -0.09
    Ïĥμ
    -0.09
     Ven
    -0.09
    POSITIVE LOGITS
     tomato
    0.33
     tomatoes
    0.30
     Tomato
    0.30
    Tom
    0.27
     Tom
    0.26
    tom
    0.23
    .tom
    0.21
     TOM
    0.20
     tom
    0.19
     ÑĤом
    0.19
    Activations Density 0.058%

    No Known Activations