© 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. 55237
    Prev
    Next
    INDEX
    Explanations

    medical treatments and conditions

    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
    ergy
    -0.10
     newsp
    -0.09
    avers
    -0.09
     abnormal
    -0.09
    iro
    -0.09
    483
    -0.09
     Crimes
    -0.09
    antry
    -0.08
     Sadd
    -0.08
     Diseases
    -0.08
    POSITIVE LOGITS
     patients
    0.14
     Mell
    0.13
     mell
    0.13
     simplex
    0.12
     vulgar
    0.11
    ous
    0.11
     nerv
    0.10
    ribbon
    0.10
    iform
    0.10
     Cohen
    0.10
    Activations Density 0.116%

    No Known Activations