© 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. 63064
    Prev
    Next
    INDEX
    Explanations

    you/vous/siz

    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
     ÑĤебе
    -0.17
     thy
    -0.17
     ÏĥοÏħ
    -0.16
     Ø®ÙĪدش
    -0.15
     ÑĤебÑı
    -0.15
     thou
    -0.15
     Thy
    -0.15
     senin
    -0.14
     themselves
    -0.14
     ÑĤобÑĸ
    -0.14
    POSITIVE LOGITS
     yourselves
    0.39
    ä½łä»¬
    0.34
     можеÑĤе
    0.26
    siniz
    0.22
     yourself
    0.20
     Ú©ÙĨÛĮد
    0.20
     باشÛĮد
    0.19
     vous
    0.17
    ÙĥÙħ
    0.17
    sınız
    0.16
    Activations Density 0.169%

    No Known Activations