© 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. 63795
    Prev
    Next
    INDEX
    Explanations

    comparisons, superiority, and terms

    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
     compared
    -0.15
    è·Ŀ
    -0.11
    æ¯Ķ
    -0.09
    .:.:.:.:.:.:.:.:
    -0.09
     worm
    -0.09
    iza
    -0.09
     пÑĢоÑĤи
    -0.09
    ipe
    -0.09
    amon
    -0.09
    符åIJĪ
    -0.08
    POSITIVE LOGITS
     counterparts
    0.16
     counterpart
    0.15
     regarding
    0.15
     terms
    0.13
    à¹ĥà¸Ļà¸ģาร
    0.12
    terms
    0.10
     Toni
    0.10
     regards
    0.10
    Regarding
    0.10
     chá»Ĺ
    0.10
    Activations Density 0.151%

    No Known Activations