© 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. 63166
    Prev
    Next
    INDEX
    Explanations

    comma-separated snacks

    np_acts-logits-general · gemini-2.5-flash-lite

    enumerations of snack foods presented as example lists, especially following an introductory phrase and joined by commas and a conjunction.

    oai_token-act-pair · gpt-5Triggered by @bestetascii
    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
     pancakes
    -0.11
     dessert
    -0.10
    Soup
    -0.10
    æĮ
    -0.10
     gravy
    -0.10
     hamburger
    -0.10
     starter
    -0.10
     Playground
    -0.09
     Dess
    -0.09
     Starter
    -0.09
    POSITIVE LOGITS
     snacks
    0.21
     snack
    0.19
     bars
    0.18
     jer
    0.18
     gran
    0.18
     trail
    0.17
     Sn
    0.17
     dried
    0.15
     pret
    0.15
    bars
    0.14
    Activations Density 0.048%

    No Known Activations