© 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. 37321
    Prev
    Next
    INDEX
    Explanations

    midnight

    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
     Noon
    -0.23
     afternoon
    -0.22
     dusk
    -0.20
     noon
    -0.19
    noon
    -0.18
     daytime
    -0.17
    å¤ķ
    -0.17
     sunset
    -0.16
     lunch
    -0.15
     sund
    -0.14
    POSITIVE LOGITS
     midnight
    0.33
     Midnight
    0.29
     late
    0.24
    mid
    0.23
     MID
    0.23
    åĩĮ
    0.23
    Mid
    0.21
     wee
    0.20
    late
    0.19
    (mid
    0.18
    Activations Density 0.082%

    No Known Activations