© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 16542
    Prev
    Next
    INDEX
    Explanations

    kissing and hugging

    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
     kisses
    -0.18
     kissed
    -0.16
     mouths
    -0.15
     kiss
    -0.15
     kissing
    -0.13
    -mouth
    -0.13
     Kiss
    -0.12
     lips
    -0.11
     Mouth
    -0.11
     mouth
    -0.11
    POSITIVE LOGITS
     fond
    0.15
     tongue
    0.14
     ca
    0.14
     nib
    0.12
     tong
    0.12
     Tong
    0.11
     mur
    0.11
     mo
    0.11
    ca
    0.11
     Fond
    0.10
    Activations Density 0.017%

    No Known Activations