© 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. 35171
    Prev
    Next
    INDEX
    Explanations

    subject + auxiliary verb

    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
     youre
    -0.09
     Hale
    -0.08
    anton
    -0.08
    itler
    -0.08
    lixir
    -0.08
    ãģ®ãģĮ
    -0.08
    uien
    -0.07
    ä¹Łæĺ¯
    -0.07
     counterpart
    -0.07
    ä¹Łä¸į
    -0.07
    POSITIVE LOGITS
     has
    0.23
     have
    0.23
     telah
    0.23
     Äijã
    0.21
     heeft
    0.17
    _have
    0.17
     Have
    0.17
     hath
    0.17
     had
    0.16
    've
    0.16
    Activations Density 0.065%

    No Known Activations