© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38500
    Prev
    Next
    INDEX
    Explanations

    too [adjective] constructions

    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
    Negative Logits
     enough
    -0.15
     Enough
    -0.11
     bel
    -0.10
     Äijủ
    -0.10
    eyer
    -0.10
    afa
    -0.10
    -sized
    -0.10
     ãĤĿ
    -0.09
     Germ
    -0.09
    ä¸įäºĨ
    -0.09
    POSITIVE LOGITS
    -too
    0.14
    Too
    0.13
     Too
    0.13
     too
    0.12
     Äijá»ĥ
    0.12
     太
    0.12
    /to
    0.11
    assy
    0.11
     demasi
    0.11
    太
    0.11
    Activations Density 0.043%

    No Known Activations