© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44514
    Prev
    Next
    INDEX
    Explanations

    sense of discomfort or pain

    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
     choking
    -0.11
    SED
    -0.09
    aksi
    -0.09
    æħİ
    -0.09
     relax
    -0.09
     (*((
    -0.09
     disgust
    -0.09
    SION
    -0.09
    _HAVE
    -0.09
     ret
    -0.09
    POSITIVE LOGITS
     discomfort
    0.19
     uncomfortable
    0.18
     crank
    0.14
     uncomfort
    0.13
     rum
    0.13
     unpleasant
    0.11
     Hunger
    0.11
     hourly
    0.10
    é
    0.10
     fam
    0.10
    Activations Density 0.086%

    No Known Activations