© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38839
    Prev
    Next
    INDEX
    Explanations

    Bruce Lee, novels, Dr

    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
    fang
    -0.11
     Korean
    -0.10
     Zhu
    -0.09
     jin
    -0.09
    ymous
    -0.09
     Lana
    -0.09
    yang
    -0.09
    .unwrap
    -0.09
    ablish
    -0.09
    aoke
    -0.09
    POSITIVE LOGITS
     Ip
    0.15
     Sha
    0.14
     Jackie
    0.14
    Mui
    0.11
    Sha
    0.11
     Chow
    0.11
     Fist
    0.11
    Ip
    0.11
     Chan
    0.10
    PKG
    0.10
    Activations Density 0.032%

    No Known Activations