© 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. 34736
    Prev
    Next
    INDEX
    Explanations

    morning and early routines

    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
     sunset
    -0.24
     dusk
    -0.22
    å¤ķ
    -0.18
     evenings
    -0.17
     afternoon
    -0.17
     Evening
    -0.17
     dinner
    -0.17
     evening
    -0.16
     Dinner
    -0.15
    æĻļ
    -0.15
    POSITIVE LOGITS
     morning
    0.48
     breakfast
    0.44
     Morning
    0.41
     mornings
    0.40
     Breakfast
    0.39
    Morning
    0.36
    æĻ¨
    0.35
     ìķĦ침
    0.29
    mor
    0.29
     early
    0.27
    Activations Density 0.229%

    No Known Activations