© 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. 55890
    Prev
    Next
    INDEX
    Explanations

    legal assistant

    np_acts-logits-general · gemini-2.5-flash-lite

    structured, numbered section headers and expository text describing generative AI applications for legal research and data analysis

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     scand
    -0.09
     legitimate
    -0.09
     Lambert
    -0.09
    luet
    -0.08
     plac
    -0.08
     Trit
    -0.08
     advent
    -0.08
     lieu
    -0.08
     Pell
    -0.08
    uling
    -0.08
    POSITIVE LOGITS
     law
    0.38
     legal
    0.35
     Law
    0.33
     Legal
    0.29
    law
    0.28
    æ³ķ
    0.27
    æ³ķå¾ĭ
    0.27
     æ³ķ
    0.27
    Legal
    0.26
    legal
    0.26
    Activations Density 0.156%

    No Known Activations