© 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. 54359
    Prev
    Next
    INDEX
    Explanations

    court proceedings being brought

    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
     orient
    -0.10
     solic
    -0.10
    æľĭ
    -0.10
    æĵį
    -0.09
     unauthorized
    -0.09
     prosecution
    -0.09
     prosecuting
    -0.09
    undred
    -0.09
     prosecutions
    -0.09
     prohibited
    -0.08
    POSITIVE LOGITS
     warrant
    0.25
     WARRANT
    0.23
     warrants
    0.22
     search
    0.17
     served
    0.16
     Garn
    0.15
     seizure
    0.14
     order
    0.14
     compelling
    0.14
     Attachment
    0.14
    Activations Density 0.024%

    No Known Activations