© 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. 24844
    Prev
    Next
    INDEX
    Explanations

    stroke and physical health

    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
     cardiovascular
    -0.24
     Cardio
    -0.23
     hearts
    -0.20
     Hearts
    -0.19
     heartbeat
    -0.16
     cardio
    -0.15
     srdce
    -0.13
     cardinal
    -0.12
     kalp
    -0.12
     cards
    -0.12
    POSITIVE LOGITS
     stroke
    0.17
     lungs
    0.15
     soul
    0.14
    stroke
    0.13
    Stroke
    0.13
    icle
    0.12
     Stroke
    0.12
     brain
    0.12
     strokes
    0.11
    brain
    0.11
    Activations Density 0.045%

    No Known Activations