© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 32821
    Prev
    Next
    INDEX
    Explanations

    Korean noun phrases

    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
     sobie
    -0.12
    ãģ¨ãģĹãģŁ
    -0.12
    лÑıли
    -0.11
    ëłĢ
    -0.10
    ãģ¨ãģĻãĤĭ
    -0.10
    ãģĹãģ¦ãģĦãĤĭ
    -0.10
    ëIJ
    -0.10
     ëĭ¤ìļ´ë°Ľê¸°
    -0.10
    ãĤģãģŁ
    -0.10
     Knox
    -0.10
    POSITIVE LOGITS
    ãģķãĤĮãĤĭ
    0.25
    ãģķãĤĮ
    0.20
    ãģķãĤĮãģŁ
    0.20
     worden
    0.16
    ãģķãĤĮãģ¦ãģĦãĤĭ
    0.16
    ãģķãĤĮãģ¦
    0.16
    ãĤīãĤĮãĤĭ
    0.14
    ãĤıãĤĮãĤĭ
    0.14
    ÏĦαι
    0.14
    ÑģÑı
    0.14
    Activations Density 0.051%

    No Known Activations