© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 23616
    Prev
    Next
    INDEX
    Explanations

    diabetes type / diabetes mellitus

    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
    airo
    -0.10
    ¶Į
    -0.09
    _DISABLED
    -0.09
     indo
    -0.08
     anchor
    -0.08
     Weiner
    -0.08
    gorith
    -0.08
     Shuffle
    -0.08
    al
    -0.08
    omo
    -0.08
    POSITIVE LOGITS
     mell
    0.35
     Mell
    0.29
     Type
    0.16
    (Type
    0.13
     type
    0.12
     tipo
    0.12
    abetes
    0.12
    (type
    0.11
     neph
    0.11
     Tipo
    0.11
    Activations Density 0.014%

    No Known Activations