© 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. 17547
    Prev
    Next
    INDEX
    Explanations

    am/pm time expressions

    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
     midnight
    -0.10
    apg
    -0.09
     Noon
    -0.09
     evenings
    -0.09
     Cust
    -0.09
    åij¨å¹´
    -0.08
     plain
    -0.08
    agar
    -0.08
    inery
    -0.08
     bank
    -0.08
    POSITIVE LOGITS
    /pm
    0.16
    sharp
    0.16
     sharp
    0.13
     Pacific
    0.13
     GMT
    0.12
     pac
    0.12
     local
    0.12
    EST
    0.12
     Uhr
    0.12
    eters
    0.12
    Activations Density 0.041%

    No Known Activations