© 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. 28291
    Prev
    Next
    INDEX
    Explanations

    I was wondering

    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
     expect
    -0.09
     blas
    -0.09
    947
    -0.08
     rak
    -0.08
     Beat
    -0.08
    odem
    -0.08
    ize
    -0.08
     Newly
    -0.08
    ges
    -0.08
    idd
    -0.08
    POSITIVE LOGITS
     wondered
    0.37
     wondering
    0.35
     wonder
    0.30
     Wonder
    0.29
    Wonder
    0.24
     wonders
    0.22
     hoping
    0.18
     hoped
    0.17
     Wonderland
    0.16
     thought
    0.13
    Activations Density 0.213%

    No Known Activations