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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 39248
    Prev
    Next
    INDEX
    Explanations

    hunger and appetite

    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
     Morrow
    -0.10
    °}
    -0.09
     Vul
    -0.09
     Pruitt
    -0.09
     eff
    -0.09
     pulp
    -0.08
     drinking
    -0.08
    787
    -0.08
     Variant
    -0.08
    /|
    -0.08
    POSITIVE LOGITS
     hunger
    0.47
     Hunger
    0.44
     hungry
    0.42
     голод
    0.39
     Hung
    0.37
    Hung
    0.36
    hung
    0.35
     appetite
    0.32
     stomach
    0.28
    unger
    0.27
    Activations Density 0.092%

    No Known Activations