© 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
    5. 50-RESID-POST-GF
    7. 34788
    Prev
    Next
    INDEX
    Explanations

    defines or describes concepts

    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
    ä¸įæĺ¯
    -0.14
     nejen
    -0.13
    æĹ¢
    -0.11
    ãģ§ãģ¯ãģªãģı
    -0.09
    :not
    -0.09
    ãģłãģijãģ§
    -0.09
     EITHER
    -0.09
    ema
    -0.09
    ãĤĪãĤĬãĤĤ
    -0.09
    éĻ¤äºĨ
    -0.09
    POSITIVE LOGITS
     actually
    0.16
     actively
    0.13
     entire
    0.12
    æķ´ä¸ª
    0.12
     actual
    0.12
    actually
    0.12
    ãĤ
    0.11
     downright
    0.11
    ãĤĢ
    0.11
     also
    0.11
    Activations Density 0.103%

    No Known Activations