© 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. 16219
    Prev
    Next
    INDEX
    Explanations

    what someone wants or needs

    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
    requete
    -0.09
    onth
    -0.09
     Bust
    -0.09
     Intent
    -0.09
    cip
    -0.09
    atar
    -0.09
     Sabb
    -0.08
    swith
    -0.08
     desperate
    -0.08
    POSITIVE LOGITS
     want
    0.32
     wants
    0.29
     muá»ijn
    0.27
     ÑħоÑĩÑĥ
    0.24
     wanted
    0.22
    è¦ģ
    0.21
     veut
    0.21
     ÑħоÑĩ
    0.21
     quiero
    0.21
     quiere
    0.20
    Activations Density 0.107%

    No Known Activations