© 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. 10751
    Prev
    Next
    INDEX
    Explanations

    take action and steps

    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
    cth
    -0.10
     heed
    -0.10
     precaution
    -0.09
    prise
    -0.09
    berapa
    -0.09
    ï½£
    -0.09
    adin
    -0.09
     preventative
    -0.08
    lse
    -0.08
    621
    -0.08
    POSITIVE LOGITS
     steps
    0.32
     measures
    0.27
     action
    0.27
     actions
    0.25
     Steps
    0.23
    steps
    0.23
    è¡ĮåĬ¨
    0.22
    Steps
    0.21
     Measures
    0.20
    æݪæĸ½
    0.19
    Activations Density 0.020%

    No Known Activations