© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 14682
    Prev
    Next
    INDEX
    Explanations

    want or desire

    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
    elez
    -0.09
    оÑĤÑĮ
    -0.09
     anticipated
    -0.09
    оÑĤÑı
    -0.09
    ä¹Ĥ
    -0.09
    ãĤĿ
    -0.09
     TRY
    -0.09
    ekil
    -0.09
     aspiring
    -0.08
    -purpose
    -0.08
    POSITIVE LOGITS
     muá»ijn
    0.50
     want
    0.46
     wants
    0.45
    æĥ³è¦ģ
    0.44
    Want
    0.38
     ingin
    0.38
     wanted
    0.37
    want
    0.37
     Want
    0.33
     desire
    0.33
    Activations Density 0.546%

    No Known Activations