© 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. 33756
    Prev
    Next
    INDEX
    Explanations

    Supreme Court

    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
     appeal
    -0.09
     appellate
    -0.09
     Appeal
    -0.09
     Bentley
    -0.09
     jury
    -0.09
     recharge
    -0.09
     opposed
    -0.09
     purge
    -0.08
    ijke
    -0.08
     appeals
    -0.08
    POSITIVE LOGITS
     Supreme
    0.22
     SC
    0.19
     Chief
    0.18
    Chief
    0.17
     justices
    0.17
     dissent
    0.16
    SC
    0.15
    (SC
    0.15
     Scot
    0.15
     Scalia
    0.14
    Activations Density 0.026%

    No Known Activations