© 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. 18571
    Prev
    Next
    INDEX
    Explanations

    subject followed by modal verb

    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
     Willis
    -0.11
    804
    -0.09
    evi
    -0.09
    :indexPath
    -0.09
    Aceptar
    -0.09
     Could
    -0.09
    ILLED
    -0.09
    ILLS
    -0.09
    erable
    -0.08
    648
    -0.08
    POSITIVE LOGITS
     should
    0.28
     will
    0.24
    should
    0.22
     sẽ
    0.22
    åºĶ该
    0.20
     likely
    0.19
    will
    0.18
     Should
    0.17
    Should
    0.17
    'll
    0.17
    Activations Density 0.103%

    No Known Activations