© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 2285
    Prev
    Next
    INDEX
    Explanations

    balanced diet and quality

    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
     gourmet
    -0.09
    å¼¥
    -0.09
    çµ
    -0.09
     dep
    -0.08
     fert
    -0.08
    abcdefghijkl
    -0.08
     hur
    -0.08
    208
    -0.08
    647
    -0.08
     nutrient
    -0.08
    POSITIVE LOGITS
     diet
    0.35
     Diet
    0.25
     balanced
    0.20
    diet
    0.19
     diets
    0.18
    -bal
    0.17
    balanced
    0.16
     dieta
    0.15
     Balanced
    0.14
    iet
    0.13
    Activations Density 0.024%

    No Known Activations