© 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. 5363
    Prev
    Next
    INDEX
    Explanations

    correcting spelling or wording

    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
    .IContainer
    -0.09
     Maver
    -0.09
     Machinery
    -0.08
     جÙĩ
    -0.08
    Charset
    -0.08
     ä»»
    -0.08
    ilda
    -0.08
     undes
    -0.08
    tae
    -0.08
     fest
    -0.08
    POSITIVE LOGITS
     should
    0.31
    åºĶ该
    0.29
     correct
    0.29
     Should
    0.26
    should
    0.26
    æŃ£ç¡®
    0.25
    Should
    0.24
    åºĶ
    0.22
     deber
    0.22
    æĩī
    0.21
    Activations Density 0.174%

    No Known Activations