© 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. 64220
    Prev
    Next
    INDEX
    Explanations

    moderate, moderation, responsible, excess

    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
     Liberties
    -0.09
     bottle
    -0.09
    643
    -0.09
     Env
    -0.09
     Ramp
    -0.08
    맼
    -0.08
    CLS
    -0.08
    inals
    -0.08
     presenter
    -0.08
    änger
    -0.08
    POSITIVE LOGITS
     moderation
    0.41
     Moder
    0.35
    Moder
    0.35
     moderate
    0.35
     Moderate
    0.28
     ÑĥмеÑĢ
    0.27
     moder
    0.27
    mod
    0.27
     moderated
    0.23
     MOD
    0.22
    Activations Density 0.061%

    No Known Activations