Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65472
    Prev
    Next
    INDEX
    Explanations

    once upon a time

    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
    ovah
    -0.09
     rh
    -0.09
    reff
    -0.09
     ÑĤв
    -0.08
    uckles
    -0.08
    ahas
    -0.08
    marks
    -0.08
    /&
    -0.08
    adel
    -0.08
    ellen
    -0.08
    POSITIVE LOGITS
     once
    0.26
     Once
    0.21
    Once
    0.21
    once
    0.20
     somewhere
    0.17
    _once
    0.15
     einmal
    0.15
     eens
    0.14
    æĽ¾
    0.14
     vez
    0.14
    Activations Density 0.199%

    No Known Activations