© 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. 5623
    Prev
    Next
    INDEX
    Explanations

    agent or character movement

    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
     Carousel
    -0.09
     lick
    -0.09
    heim
    -0.09
    Neighbor
    -0.09
    Ju
    -0.09
     Ju
    -0.09
    regnum
    -0.08
     Neighbor
    -0.08
    ¨¨
    -0.08
    ĵĺ
    -0.08
    POSITIVE LOGITS
     avatar
    0.20
     character
    0.20
     player
    0.18
     cursor
    0.17
     characters
    0.16
     hero
    0.16
     agent
    0.15
     Avatar
    0.15
     agents
    0.15
     protagonist
    0.15
    Activations Density 0.143%

    No Known Activations