© 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. 34438
    Prev
    Next
    INDEX
    Explanations

    social circles or networks

    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
     comrades
    -0.12
     teammate
    -0.11
     Neighbor
    -0.11
     fellow
    -0.10
     neighbor
    -0.10
     colleague
    -0.10
     glo
    -0.09
    omen
    -0.09
     bil
    -0.09
     neighbour
    -0.09
    POSITIVE LOGITS
     circle
    0.49
     circles
    0.42
    circle
    0.37
     Circle
    0.37
    åľĪ
    0.35
    Circle
    0.34
     networks
    0.34
    -circle
    0.33
     network
    0.33
    _circle
    0.28
    Activations Density 0.109%

    No Known Activations