© 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. 4830
    Prev
    Next
    INDEX
    Explanations

    clients, developers, admin, industry

    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
     consumers
    -0.13
     customers
    -0.12
     audiences
    -0.12
     humans
    -0.12
    Humans
    -0.11
     individuals
    -0.11
     Customers
    -0.10
    çļĦ人
    -0.10
    人们
    -0.10
     Consumers
    -0.10
    POSITIVE LOGITS
    roker
    0.10
     Petit
    0.10
     staff
    0.09
    /downloads
    0.09
     canh
    0.09
    caret
    0.09
    âĢIJ'
    0.08
     Bar
    0.08
    InputLabel
    0.08
    avern
    0.08
    Activations Density 0.133%

    No Known Activations