© 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. 18620
    Prev
    Next
    INDEX
    Explanations

    pronouns as subjects

    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
    uzzi
    -0.10
    aukee
    -0.10
    ssf
    -0.09
     ãĤĿ
    -0.09
    ãģĿãĤĵãģª
    -0.09
    plus
    -0.09
    å°¤
    -0.09
    ï¼ĮæľĢ
    -0.08
    icus
    -0.08
    tc
    -0.08
    POSITIVE LOGITS
     They
    0.11
    They
    0.10
     It
    0.09
    It
    0.09
     era
    0.09
    263
    0.09
     they
    0.09
     specifically
    0.09
    Instant
    0.09
    alat
    0.09
    Activations Density 0.055%

    No Known Activations