© 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. 59396
    Prev
    Next
    INDEX
    Explanations

    are you asking a question

    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
     probably
    -0.11
     Probably
    -0.10
     either
    -0.10
    either
    -0.10
    ç§ģãģ¯
    -0.10
     neither
    -0.10
    probably
    -0.09
    俺ãģ¯
    -0.09
    916
    -0.09
    313
    -0.09
    POSITIVE LOGITS
     perhaps
    0.15
     etwa
    0.15
     finally
    0.14
     denn
    0.14
     perch
    0.14
    —;are
    0.12
    æľ¬å½ĵãģ«
    0.12
     yoksa
    0.12
     snad
    0.11
    -нибÑĥдÑĮ
    0.11
    Activations Density 0.056%

    No Known Activations