© 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. 22688
    Prev
    Next
    INDEX
    Explanations

    each or every

    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
     annual
    -0.14
     Annual
    -0.13
    Annual
    -0.13
    annual
    -0.11
     Everyday
    -0.10
     Everything
    -0.10
     Weekly
    -0.10
     Monthly
    -0.10
     yearly
    -0.09
    esis
    -0.09
    POSITIVE LOGITS
     each
    0.75
    each
    0.61
     má»Ĺi
    0.54
    æ¯ı
    0.54
     Each
    0.53
     cada
    0.52
    Each
    0.51
     chaque
    0.51
     каждÑĭй
    0.50
     EACH
    0.48
    Activations Density 0.284%

    No Known Activations