© 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. 19411
    Prev
    Next
    INDEX
    Explanations

    is he's contraction

    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
    *****/\n
    -0.10
    ackle
    -0.09
    Å¡il
    -0.09
    weis
    -0.09
    /terms
    -0.08
    Ｌ
    -0.08
     oppon
    -0.08
    stor
    -0.08
    âĶĺ
    -0.08
    'gc
    -0.08
    POSITIVE LOGITS
     verb
    0.18
     aux
    0.15
     auxiliary
    0.14
    Aux
    0.14
     cop
    0.14
     Verb
    0.13
     être
    0.13
     BE
    0.13
    -being
    0.13
     Auxiliary
    0.12
    Activations Density 0.090%

    No Known Activations