© 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. 26266
    Prev
    Next
    INDEX
    Explanations

    extracurricular activities and extract

    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
     better
    -0.12
     Easily
    -0.10
    owler
    -0.09
     easier
    -0.09
    ìĹŃ
    -0.09
     straightforward
    -0.09
     nearby
    -0.09
     easily
    -0.09
    better
    -0.09
     less
    -0.09
    POSITIVE LOGITS
    æīįèĥ½
    0.17
     possibly
    0.12
     delicate
    0.12
     delic
    0.12
     potentially
    0.11
     numerous
    0.11
     jugg
    0.10
     complex
    0.10
     constantly
    0.10
     effectively
    0.10
    Activations Density 0.116%

    No Known Activations