© 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. 42157
    Prev
    Next
    INDEX
    Explanations

    laws and jurisdiction

    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
    åħ¨åĽ½
    -0.10
     generation
    -0.09
    京
    -0.09
    ãĢĢr
    -0.09
     Presidents
    -0.09
    人åı£
    -0.09
     continents
    -0.09
    >NN
    -0.09
    opsy
    -0.09
    psc
    -0.08
    POSITIVE LOGITS
     jurisdiction
    0.26
     jurisdictions
    0.23
     countries
    0.21
     country
    0.21
     Jur
    0.17
    jur
    0.17
    Jur
    0.17
     paÃŃs
    0.15
     Country
    0.15
    country
    0.15
    Activations Density 0.067%

    No Known Activations