© 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. 8247
    Prev
    Next
    INDEX
    Explanations

    you smile or look at me

    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
     ourselves
    -0.19
    ä½łä»¬
    -0.14
     euch
    -0.13
     YOU
    -0.12
     ìŬ룬ë¶Ħ
    -0.12
    ensa
    -0.10
     usted
    -0.10
    agen
    -0.09
    ietet
    -0.09
     Ihnen
    -0.09
    POSITIVE LOGITS
     me
    0.37
     yourself
    0.36
    ç»ĻæĪij
    0.30
     мне
    0.26
    æĪij
    0.24
    让æĪij
    0.24
     Yourself
    0.24
     менÑı
    0.22
     my
    0.21
     mnie
    0.20
    Activations Density 0.242%

    No Known Activations