© 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. 23177
    Prev
    Next
    INDEX
    Explanations

    acts of kindness and support

    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
    ID
    -0.10
    apat
    -0.09
    _Handler
    -0.09
    _GUI
    -0.08
     Sirius
    -0.08
     lý
    -0.08
    lemn
    -0.08
    å¼·
    -0.08
     particip
    -0.08
     Sinai
    -0.08
    POSITIVE LOGITS
     acts
    0.38
     act
    0.30
     gesture
    0.30
     Acts
    0.29
    acts
    0.28
    Acts
    0.28
     gestures
    0.27
     deeds
    0.23
     deed
    0.23
     kindness
    0.23
    Activations Density 0.117%

    No Known Activations