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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 34000
    Prev
    Next
    INDEX
    Explanations

    formal and professional writing

    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
    atra
    -0.10
    ingu
    -0.09
     original
    -0.09
     privately
    -0.09
    éłĨ
    -0.09
     Original
    -0.08
    Latch
    -0.08
     rel
    -0.08
    IXEL
    -0.08
    /original
    -0.08
    POSITIVE LOGITS
     formal
    0.45
     Formal
    0.39
    æŃ£å¼ı
    0.33
     رسÙħÛĮ
    0.21
     professional
    0.19
    /form
    0.19
    ORMAL
    0.19
     official
    0.19
     formally
    0.17
     serious
    0.17
    Activations Density 0.180%

    No Known Activations