© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 19589
    Prev
    Next
    INDEX
    Explanations

    final or unknown information

    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
     Earlier
    -0.11
     Substitute
    -0.10
    ingu
    -0.10
     First
    -0.10
     tops
    -0.09
    æĹ©
    -0.09
    Earlier
    -0.09
    First
    -0.08
     Previous
    -0.08
     numerator
    -0.08
    POSITIVE LOGITS
     latter
    0.45
     last
    0.38
    æľĢåIJİ
    0.36
    æľĢå¾Į
    0.32
     cuá»iji
    0.30
     final
    0.29
     поÑģлед
    0.29
     ë§Īì§Ģë§ī
    0.28
    last
    0.28
     último
    0.27
    Activations Density 0.085%

    No Known Activations