© 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. 8526
    Prev
    Next
    INDEX
    Explanations

    oranges and fruits

    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
     Flowers
    -0.12
     flowers
    -0.12
     barley
    -0.12
     wheat
    -0.12
     Flower
    -0.12
     жиÑĢ
    -0.11
     Wheat
    -0.11
     maize
    -0.11
     Grain
    -0.10
     rice
    -0.10
    POSITIVE LOGITS
     fruit
    0.29
     Fruit
    0.23
    fruit
    0.22
    æŀľ
    0.20
     fruits
    0.20
     bru
    0.20
     ju
    0.19
     फल
    0.18
     juice
    0.18
     ÑĦÑĢÑĥкÑĤ
    0.18
    Activations Density 0.203%

    No Known Activations