© 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. 38989
    Prev
    Next
    INDEX
    Explanations

    may be, may have, he then

    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
     apparently
    -0.13
     reportedly
    -0.11
     seemingly
    -0.11
    Apparently
    -0.10
    æį®
    -0.10
     Apparently
    -0.10
    kes
    -0.10
    xin
    -0.10
     suspicion
    -0.10
     Germ
    -0.09
    POSITIVE LOGITS
     possibly
    0.20
    åı¯èĥ½
    0.16
    possibly
    0.15
     possible
    0.13
     ÙħÙħÚ©ÙĨ
    0.13
     Possibly
    0.13
     either
    0.12
     originally
    0.11
     may
    0.11
    possible
    0.11
    Activations Density 0.103%

    No Known Activations