© 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. 21258
    Prev
    Next
    INDEX
    Explanations

    Rise Made, contract disputes

    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
    [
    -0.11
     introdu
    -0.09
    ä¿
    -0.08
    NB
    -0.08
    201
    -0.08
     sidel
    -0.08
    stru
    -0.08
     avid
    -0.08
     باÙĦÙĨ
    -0.08
     MVP
    -0.08
    POSITIVE LOGITS
     ‘;
    0.17
     '
    0.15
     intl
    0.10
     fears
    0.09
     latest
    0.09
     '_
    0.09
    -redux
    0.09
    ofilm
    0.09
     '$
    0.09
     probe
    0.08
    Activations Density 0.155%

    No Known Activations