© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33554
    Prev
    Next
    INDEX
    Explanations

    legal professional or advice

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

    mentions of legal professionals (lawyers/attorneys), including multilingual references and related professional/legal disclaimers.

    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
    ASM
    -0.11
     ASM
    -0.10
    phies
    -0.09
    -stat
    -0.09
    CTR
    -0.09
    tru
    -0.09
     Jury
    -0.08
    uml
    -0.08
     report
    -0.08
     reporting
    -0.08
    POSITIVE LOGITS
     lawyer
    0.45
     lawyers
    0.44
     attorneys
    0.39
    å¾ĭ
    0.38
     attorney
    0.38
     Lawyer
    0.34
     law
    0.33
     legal
    0.32
     Lawyers
    0.32
     lawy
    0.30
    Activations Density 0.111%

    No Known Activations