© 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. 28232
    Prev
    Next
    INDEX
    Explanations

    interpreting words and providing context

    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
     Phong
    -0.12
     Nguyen
    -0.11
    uong
    -0.10
     Jing
    -0.10
     Trang
    -0.10
     å¤ĸéĥ¨
    -0.09
    zim
    -0.09
    ç¾İåħĥ
    -0.09
    çĦ¡ãģĹãģ
    -0.09
    ãĢĢãĤ¤
    -0.09
    POSITIVE LOGITS
     Chinese
    0.19
    Chinese
    0.15
     China
    0.14
     transl
    0.14
     Han
    0.13
     Canton
    0.13
     Nie
    0.13
     Western
    0.13
     translation
    0.12
     Wade
    0.12
    Activations Density 0.352%

    No Known Activations