© 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. 36290
    Prev
    Next
    INDEX
    Explanations

    medical conditions characteristics

    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
    ;;;;;;
    -0.09
    í
    -0.09
    DRV
    -0.09
    .SizeF
    -0.08
     aggrav
    -0.08
    aths
    -0.08
    ziehung
    -0.08
     Wilkinson
    -0.08
     Printf
    -0.08
    andidate
    -0.08
    POSITIVE LOGITS
     condition
    0.28
    condition
    0.19
     Condition
    0.18
     disorder
    0.18
     conditions
    0.16
     condi
    0.16
    Condition
    0.16
     common
    0.16
     serious
    0.16
     treat
    0.15
    Activations Density 0.085%

    No Known Activations