© 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. 22975
    Prev
    Next
    INDEX
    Explanations

    Star Wars themed video

    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
     carnival
    -0.09
     mighty
    -0.09
     gardening
    -0.09
     Carnival
    -0.09
     Weekend
    -0.08
    ubo
    -0.08
    -Oct
    -0.08
     æĵ
    -0.08
     Castillo
    -0.08
    ulo
    -0.08
    POSITIVE LOGITS
     Christmas
    0.46
     Santa
    0.44
    Santa
    0.39
    Christmas
    0.38
     santa
    0.32
     December
    0.31
     christmas
    0.31
    December
    0.29
     Advent
    0.27
    ihn
    0.26
    Activations Density 0.105%

    No Known Activations