© 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. 42781
    Prev
    Next
    INDEX
    Explanations

    in operation or current state

    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
     Hir
    -0.10
     DONE
    -0.10
    abol
    -0.09
    occ
    -0.09
     where
    -0.09
     fier
    -0.09
     created
    -0.09
    ieux
    -0.09
    yt
    -0.09
    where
    -0.08
    POSITIVE LOGITS
     Äijang
    0.15
     operating
    0.15
     present
    0.14
    æŃ£åľ¨
    0.13
     Operating
    0.13
     ÑĢабоÑĤа
    0.11
     currently
    0.11
    Operating
    0.11
    ÑĥÑī
    0.11
     running
    0.11
    Activations Density 0.214%

    No Known Activations