© 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. 62561
    Prev
    Next
    INDEX
    Explanations

    was not, been eaten, is not

    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
    VI
    -0.09
     Meh
    -0.09
    991
    -0.09
     Perr
    -0.09
     sudden
    -0.08
     olursa
    -0.08
    oplan
    -0.08
     soud
    -0.08
     Ellis
    -0.08
    fy
    -0.08
    POSITIVE LOGITS
    ç«Ł
    0.12
     indeed
    0.12
     something
    0.12
    åİŁæĿ¥
    0.11
     Ñıким
    0.11
    æł¹æľ¬
    0.10
     must
    0.10
    ottes
    0.09
     worse
    0.09
     ¡
    0.09
    Activations Density 0.038%

    No Known Activations