© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35753
    Prev
    Next
    INDEX
    Explanations

    code comments introducing main sections

    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
    backend
    -0.09
    ALES
    -0.09
    ode
    -0.09
     Ùģار
    -0.09
     Wick
    -0.09
     ëĤ´
    -0.08
     Cunning
    -0.08
     nebu
    -0.08
    apist
    -0.08
    ICS
    -0.08
    POSITIVE LOGITS
     main
    0.34
    main
    0.29
     Main
    0.26
     MAIN
    0.25
    Main
    0.24
    MAIN
    0.23
    _main
    0.22
    /main
    0.21
    .main
    0.21
    (main
    0.20
    Activations Density 0.055%

    No Known Activations