© 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. 15592
    Prev
    Next
    INDEX
    Explanations

    large datasets and data mining

    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
    æ·»
    -0.10
    /******/
    -0.10
    zia
    -0.10
    agara
    -0.09
    uxtap
    -0.09
    åª
    -0.09
    ñas
    -0.09
    antro
    -0.09
    inspace
    -0.09
     ï¾Ĭ
    -0.09
    POSITIVE LOGITS
     vast
    0.22
     data
    0.21
     large
    0.18
     raw
    0.17
    data
    0.17
     sets
    0.16
     ter
    0.15
    large
    0.15
     datasets
    0.15
     huge
    0.14
    Activations Density 0.139%

    No Known Activations