© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1699
    Prev
    Next
    INDEX
    Explanations

    PyTorch library usage

    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
    .scalablytyped
    -0.11
    /Internal
    -0.10
    -gnu
    -0.09
     Roose
    -0.09
    empor
    -0.09
    SF
    -0.09
    enant
    -0.09
    acher
    -0.09
    pcf
    -0.09
    ĥģ
    -0.09
    POSITIVE LOGITS
    torch
    0.21
     torch
    0.15
     Py
    0.13
     Torch
    0.13
     py
    0.12
    ör
    0.11
     ï¾ī
    0.10
    /py
    0.10
    raz
    0.10
    xis
    0.10
    Activations Density 0.017%

    No Known Activations