© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1123
    Prev
    Next
    INDEX
    Explanations

    gentle slower steady preserve steady

    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
     raw
    -0.11
     dynam
    -0.11
     masculine
    -0.10
     há»
    -0.10
     subtly
    -0.10
     exped
    -0.09
    Bold
    -0.09
    ç²Ĺ
    -0.09
     mạnh
    -0.09
     kinetic
    -0.09
    POSITIVE LOGITS
     slower
    0.24
     slow
    0.24
     gent
    0.23
     gentle
    0.20
    gent
    0.19
    slow
    0.18
     softer
    0.16
    æŁĶ
    0.15
     steady
    0.15
    æħ¢
    0.15
    Activations Density 0.222%

    No Known Activations