© 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. 9374
    Prev
    Next
    INDEX
    Explanations

    kidney stones treatment or risks

    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
     tr
    -0.10
     cervical
    -0.10
     wound
    -0.09
     Plex
    -0.09
    erland
    -0.09
     thor
    -0.09
    ewan
    -0.09
     Hansen
    -0.09
     edi
    -0.09
     opportun
    -0.09
    POSITIVE LOGITS
     stones
    0.31
     stone
    0.28
     Stones
    0.24
     lith
    0.23
     neph
    0.22
    stones
    0.21
     Lith
    0.20
    olith
    0.20
     Stone
    0.19
     kidney
    0.19
    Activations Density 0.035%

    No Known Activations