© 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. 43953
    Prev
    Next
    INDEX
    Explanations

    Korean words containing `ë§IJ`

    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
    ë¨
    -0.10
     Buchanan
    -0.10
    atum
    -0.10
    身ä¸Ĭ
    -0.09
    íģ¼
    -0.09
     Sev
    -0.09
    ëį°ìĿ´íĬ¸
    -0.09
    ãĤĴãģĹãģŁ
    -0.09
    kers
    -0.09
    ãģĹãģ¦ãĤĭ
    -0.08
    POSITIVE LOGITS
    ìĿĦ
    0.10
    ëŀį
    0.10
    ãĤĴ
    0.10
    aldi
    0.09
    åĨħ容
    0.09
     contents
    0.09
     Nim
    0.09
     íķĺëĤĺ
    0.09
     Crack
    0.09
     writ
    0.09
    Activations Density 0.078%

    No Known Activations