© 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. 27154
    Prev
    Next
    INDEX
    Explanations

    and start

    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
     sho
    -0.10
     Bien
    -0.09
    zy
    -0.09
     POD
    -0.09
     segmentation
    -0.09
     fork
    -0.09
     bust
    -0.09
     Sho
    -0.09
    há
    -0.09
     sud
    -0.09
    POSITIVE LOGITS
     easier
    0.13
    aign
    0.12
     rejo
    0.12
     conquer
    0.12
     then
    0.12
     THEN
    0.11
     each
    0.11
     hver
    0.11
     Each
    0.11
     każ
    0.10
    Activations Density 0.077%

    No Known Activations