© 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. 618
    Prev
    Next
    INDEX
    Explanations

    command or instruction sequence

    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
    -two
    -0.10
     aller
    -0.09
    ONES
    -0.09
     minden
    -0.08
    æĺ¯ä¸ª
    -0.08
    807
    -0.08
    udas
    -0.08
    ìĿ¼
    -0.08
    æĹ¢
    -0.08
     má»įi
    -0.08
    POSITIVE LOGITS
     one
    0.52
    ä¹ĭä¸Ģ
    0.50
     ÛĮÚ©ÛĮ
    0.47
     salah
    0.42
    åħ¶ä¸Ń
    0.39
     either
    0.38
     íķĺëĤĺ
    0.31
     nÄĽkter
    0.29
    either
    0.28
     eines
    0.28
    Activations Density 0.280%

    No Known Activations