© 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. 58609
    Prev
    Next
    INDEX
    Explanations

    legal precedent and jurisprudence

    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
     Bauer
    -0.12
     substantive
    -0.11
    rea
    -0.11
    ç½²
    -0.10
     unre
    -0.09
     investigation
    -0.09
     Clay
    -0.09
     Mend
    -0.09
     Ment
    -0.09
     uncover
    -0.08
    POSITIVE LOGITS
     preced
    0.25
    preced
    0.22
     precedent
    0.21
     Supreme
    0.19
     cases
    0.17
     decisions
    0.17
     precedence
    0.17
     cas
    0.15
     stare
    0.15
     holdings
    0.15
    Activations Density 0.038%

    No Known Activations