© 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. 64909
    Prev
    Next
    INDEX
    Explanations

    was placed, expected, occupied

    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
     WILL
    -0.09
    ãģĵãģ¨ãģ«
    -0.09
     пÑĢидеÑĤÑģÑı
    -0.09
     Might
    -0.08
    enti
    -0.08
    à¤Ńà¤Ĺ
    -0.08
    ï¼Ĭ
    -0.08
    669
    -0.08
    illis
    -0.08
    ScreenState
    -0.08
    POSITIVE LOGITS
     supposed
    0.60
     should
    0.40
    åºĶ该
    0.40
     suppose
    0.35
    ãģ¯ãģļ
    0.34
     Should
    0.34
    should
    0.33
    Should
    0.33
     deber
    0.33
    æĩī
    0.33
    Activations Density 0.279%

    No Known Activations