© 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. 39045
    Prev
    Next
    INDEX
    Explanations

    carefree

    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
     meanwhile
    -0.10
     abbreviated
    -0.09
     Ä°ÅŁte
    -0.08
     iÅŁte
    -0.08
    aller
    -0.08
    SURE
    -0.08
     mus
    -0.08
    astos
    -0.08
    pron
    -0.08
     interf
    -0.08
    POSITIVE LOGITS
     better
    0.21
    better
    0.18
     besser
    0.17
    æĽ´
    0.16
     Better
    0.16
    ï¼ĮæĪĸ
    0.16
     altern
    0.15
    æĪĸèĢħ
    0.15
    Better
    0.15
     OR
    0.15
    Activations Density 0.126%

    No Known Activations