© 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. 34402
    Prev
    Next
    INDEX
    Explanations

    acts of physical 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
    Not in Any Lists

    No Comments

    Negative Logits
    orio
    -0.10
     flirt
    -0.10
    oley
    -0.09
    ï¼ıï¼ı
    -0.09
     sovereign
    -0.09
     cruel
    -0.09
    uisine
    -0.09
    ialis
    -0.09
     Toy
    -0.08
    arias
    -0.08
    POSITIVE LOGITS
     hug
    0.16
    æĭ¥
    0.16
    æĬ±
    0.15
     pet
    0.15
     attention
    0.14
     rub
    0.12
     touch
    0.12
     pat
    0.12
     lav
    0.12
     lap
    0.12
    Activations Density 0.068%

    No Known Activations