© 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. 16671
    Prev
    Next
    INDEX
    Explanations

    who wants what

    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
    ä¸įå¾Ĺ
    -0.10
    ASSES
    -0.09
    ãĤĴãģ¤
    -0.08
    ome
    -0.08
     vir
    -0.08
    ekil
    -0.08
     feud
    -0.08
    pray
    -0.08
    arov
    -0.08
    iat
    -0.08
    POSITIVE LOGITS
     wish
    0.23
     muá»ijn
    0.19
     want
    0.19
     wishes
    0.17
    è¦ģ
    0.17
     wants
    0.16
     ÑħоÑĤ
    0.15
    à¹īà¸Ńà¸ĩà¸ģาร
    0.15
     ÑħоÑĩÑĥ
    0.15
     Wish
    0.15
    Activations Density 0.042%

    No Known Activations