© 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. 9655
    Prev
    Next
    INDEX
    Explanations

    main principal key most

    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
     Lowest
    -0.11
     predomin
    -0.09
     ymax
    -0.09
     predominantly
    -0.08
    iggs
    -0.08
    IGO
    -0.08
     ymin
    -0.08
    icont
    -0.08
     disproportion
    -0.08
    aska
    -0.08
    POSITIVE LOGITS
     main
    0.65
     major
    0.55
     principal
    0.50
    主è¦ģ
    0.47
     principales
    0.46
     primary
    0.42
    main
    0.39
     주ìļĶ
    0.39
    principal
    0.38
    major
    0.38
    Activations Density 0.334%

    No Known Activations