© 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. 25279
    Prev
    Next
    INDEX
    Explanations

    beach, market, dance, bakery, cream

    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
    -like
    -0.12
    zik
    -0.10
    -worthy
    -0.10
     Puzzle
    -0.09
    izes
    -0.09
     outfit
    -0.09
     aver
    -0.09
     amateur
    -0.09
     Prelude
    -0.09
     Fut
    -0.09
    POSITIVE LOGITS
     fix
    0.14
     fi
    0.13
    blr
    0.11
     magic
    0.11
     goals
    0.10
     fun
    0.10
    lisi
    0.10
    olic
    0.10
    .Formatter
    0.10
     experience
    0.10
    Activations Density 0.184%

    No Known Activations