© 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. 23200
    Prev
    Next
    INDEX
    Explanations

    diseases like cancer, Alzheimer, stroke

    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
     sickness
    -0.14
     illness
    -0.14
     health
    -0.13
     pathology
    -0.12
    ickness
    -0.12
     Health
    -0.11
     ail
    -0.11
    çĹħ
    -0.11
     neurop
    -0.11
    çĹĩ
    -0.11
    POSITIVE LOGITS
     strokes
    0.22
     stroke
    0.21
    Stroke
    0.17
    stroke
    0.17
     Stroke
    0.15
     depression
    0.14
     Cro
    0.14
     Parkinson
    0.14
     Lou
    0.13
     Huntington
    0.13
    Activations Density 0.041%

    No Known Activations