© 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. 9095
    Prev
    Next
    INDEX
    Explanations

    cup of granulated sugar

    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
    agini
    -0.10
    éĿĪ
    -0.09
     straw
    -0.09
    ãĥ¼ãĥª
    -0.09
    hiba
    -0.09
     tit
    -0.09
     Ragnar
    -0.08
    ubi
    -0.08
     Lent
    -0.08
     Um
    -0.08
    POSITIVE LOGITS
     eggs
    0.14
     sugars
    0.13
     beat
    0.13
     sugar
    0.13
     Bust
    0.12
     cup
    0.12
     Sugar
    0.12
     cream
    0.11
     beating
    0.11
    beat
    0.11
    Activations Density 0.029%

    No Known Activations