© 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. 39492
    Prev
    Next
    INDEX
    Explanations

    was in

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

    A narrative transition where a character wakes up the next morning and the immediate aftermath of that scene.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     Mast
    -0.11
     ï¼¼:
    -0.10
     Wich
    -0.09
     mast
    -0.09
    erot
    -0.09
     dinner
    -0.09
     Lung
    -0.09
    _CB
    -0.09
    llum
    -0.09
    .SDK
    -0.09
    POSITIVE LOGITS
     hang
    0.52
     Hang
    0.46
     hung
    0.44
    Hang
    0.40
    hang
    0.39
     hangs
    0.26
    hung
    0.21
    æĮĤ
    0.19
     Hung
    0.18
     headache
    0.17
    Activations Density 0.044%

    No Known Activations