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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 34767
    Prev
    Next
    INDEX
    Explanations

    sweet pick birthday

    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
     candies
    -0.11
     Candy
    -0.10
    Bubble
    -0.10
    blr
    -0.10
    ENCES
    -0.09
     crackers
    -0.09
     candy
    -0.09
     bubble
    -0.09
     pizzas
    -0.09
    optic
    -0.09
    POSITIVE LOGITS
     dough
    0.19
     Dunk
    0.15
     Dough
    0.15
     dunk
    0.15
     yeast
    0.15
     hole
    0.15
     holes
    0.14
     Kris
    0.14
     Hole
    0.13
     Homer
    0.13
    Activations Density 0.033%

    No Known Activations