© 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. 21461
    Prev
    Next
    INDEX
    Explanations

    nursing or becoming successful

    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
     Physicians
    -0.12
    ichern
    -0.10
     Doctors
    -0.10
     veterin
    -0.10
     lim
    -0.10
     physicians
    -0.10
     camps
    -0.09
     Veter
    -0.09
     household
    -0.09
    ULO
    -0.09
    POSITIVE LOGITS
     scrub
    0.23
     RN
    0.20
     nursing
    0.19
     param
    0.19
     LP
    0.18
    RN
    0.17
     Param
    0.17
     Nursing
    0.15
     ward
    0.15
     shift
    0.15
    Activations Density 0.092%

    No Known Activations