© 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. 34191
    Prev
    Next
    INDEX
    Explanations

    serve and enjoy

    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
     scratch
    -0.11
     clipboard
    -0.10
     Davies
    -0.09
    roscope
    -0.09
    utra
    -0.09
    Cream
    -0.09
    ãģĿ
    -0.09
    scratch
    -0.08
    etry
    -0.08
    ict
    -0.08
    POSITIVE LOGITS
     serve
    0.26
     Serve
    0.25
    Serve
    0.25
     served
    0.25
     serving
    0.23
     Enjoy
    0.22
    serve
    0.22
     enjoy
    0.21
     serves
    0.20
    Enjoy
    0.20
    Activations Density 0.023%

    No Known Activations