© 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. 53833
    Prev
    Next
    INDEX
    Explanations

    discomfort and curiosity

    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
    æģ¨
    -0.10
     kork
    -0.10
    æij
    -0.09
    INU
    -0.09
    LIK
    -0.09
    ptom
    -0.09
    ufs
    -0.09
    ripper
    -0.09
     fears
    -0.09
    lime
    -0.09
    POSITIVE LOGITS
     uncomfortable
    0.54
     discomfort
    0.51
     uncomfort
    0.37
    comfort
    0.32
     Comfort
    0.29
     une
    0.29
     awkward
    0.29
    Comfort
    0.29
     comfortable
    0.28
    awk
    0.27
    Activations Density 0.114%

    No Known Activations