© 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. 46030
    Prev
    Next
    INDEX
    Explanations

    kiss and affection

    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
     Knock
    -0.10
    ido
    -0.10
     Pai
    -0.09
    432
    -0.09
     Hawth
    -0.09
    icl
    -0.09
     Shak
    -0.08
     claws
    -0.08
     wizard
    -0.08
     Haram
    -0.08
    POSITIVE LOGITS
     kiss
    0.39
     Kiss
    0.35
     kisses
    0.33
     kissed
    0.32
     kissing
    0.28
     baiser
    0.25
    åIJ
    0.23
    Âłk
    0.20
     hôn
    0.20
     lips
    0.19
    Activations Density 0.069%

    No Known Activations