© 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. 20738
    Prev
    Next
    INDEX
    Explanations

    learning materials and courses

    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
     coursework
    -0.14
     Courses
    -0.13
    Courses
    -0.12
    /classes
    -0.12
    _courses
    -0.11
     courses
    -0.11
    课ç¨ĭ
    -0.10
    igo
    -0.10
    courses
    -0.10
     classrooms
    -0.09
    POSITIVE LOGITS
     degrees
    0.13
     boot
    0.13
     Boot
    0.11
     degree
    0.11
     retreat
    0.10
    Degrees
    0.10
     MO
    0.10
    degrees
    0.10
     Degrees
    0.10
    çłĶ究æīĢ
    0.10
    Activations Density 0.029%

    No Known Activations