© 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. 29485
    Prev
    Next
    INDEX
    Explanations

    urinary system symptoms and treatment

    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
     disg
    -0.12
     Eug
    -0.09
     bre
    -0.09
    OGLE
    -0.09
     saliva
    -0.09
     Eugene
    -0.09
     íĻľìļ©
    -0.09
    наÑĢ
    -0.08
    .Actions
    -0.08
    senal
    -0.08
    POSITIVE LOGITS
     u
    0.29
     bladder
    0.27
     Ur
    0.25
     UT
    0.23
    Ur
    0.23
     urinary
    0.23
     cath
    0.22
     void
    0.20
     ur
    0.20
     stones
    0.19
    Activations Density 0.020%

    No Known Activations