© 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. 24815
    Prev
    Next
    INDEX
    Explanations

    make up or made up

    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
    ----------</
    -0.11
    -------------</
    -0.11
    nodoc
    -0.10
    iyas
    -0.10
    abwe
    -0.10
    BOOLE
    -0.10
    ~-~-
    -0.10
    UrlParser
    -0.10
    taboola
    -0.09
    chalk
    -0.09
    POSITIVE LOGITS
     made
    0.27
    made
    0.25
     Made
    0.24
     invent
    0.23
    Made
    0.22
     invention
    0.22
     invented
    0.22
     MADE
    0.21
    -up
    0.20
     fabric
    0.20
    Activations Density 0.044%

    No Known Activations