© 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. 4134
    Prev
    Next
    INDEX
    Explanations

    two main categories

    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
    iology
    -0.09
    hea
    -0.09
     ÙĪاØŃ
    -0.09
     Associates
    -0.08
    inqu
    -0.08
     confront
    -0.08
     Straw
    -0.08
     jednotlivých
    -0.08
    ocations
    -0.08
     Fon
    -0.08
    POSITIVE LOGITS
     main
    0.32
     major
    0.21
     broad
    0.18
     basic
    0.18
     types
    0.18
    main
    0.17
    (main
    0.17
    主è¦ģ
    0.17
    .main
    0.16
     camps
    0.16
    Activations Density 0.098%

    No Known Activations