© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 32678
    Prev
    Next
    INDEX
    Explanations

    remain calm or distract

    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
    Negative Logits
    ehr
    -0.10
     relieved
    -0.10
     acquitted
    -0.09
     hesitation
    -0.09
     warning
    -0.08
     заÑģÑĤ
    -0.08
    656
    -0.08
     Ñī
    -0.08
    illac
    -0.08
    imbus
    -0.08
    POSITIVE LOGITS
     cal
    0.61
     calm
    0.51
     Cal
    0.48
    cal
    0.48
     CAL
    0.37
    Cal
    0.36
    CAL
    0.33
     calming
    0.33
    -cal
    0.32
    /cal
    0.30
    Activations Density 0.092%

    No Known Activations