© 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. 54594
    Prev
    Next
    INDEX
    Explanations

    lessons learned

    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
    isu
    -0.10
     bat
    -0.09
     Meh
    -0.09
     thoughts
    -0.09
    umba
    -0.09
    enso
    -0.08
     Juda
    -0.08
    ï¼ı/
    -0.08
     loc
    -0.08
    enci
    -0.08
    POSITIVE LOGITS
     lesson
    0.44
     Lesson
    0.35
    lesson
    0.34
     lessons
    0.33
    Lesson
    0.31
     Lessons
    0.27
    lessons
    0.26
     ÑĥÑĢок
    0.22
    .lesson
    0.18
     valuable
    0.16
    Activations Density 0.018%

    No Known Activations