© 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. 16254
    Prev
    Next
    INDEX
    Explanations

    training and teaching models

    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
     automatically
    -0.10
    eyle
    -0.09
     magn
    -0.09
    ļĮ
    -0.09
     Glass
    -0.09
     Stevens
    -0.09
     comp
    -0.08
    å¥Ĺ
    -0.08
     breakout
    -0.08
     automáticamente
    -0.08
    POSITIVE LOGITS
     feeding
    0.23
     teach
    0.22
     feed
    0.21
     teaching
    0.20
     training
    0.19
    æķĻ
    0.19
     train
    0.18
    feeding
    0.17
    Feed
    0.17
     Teach
    0.17
    Activations Density 0.158%

    No Known Activations