© 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. 333
    Prev
    Next
    INDEX
    Explanations

    wisdom, having experience, make good

    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
    wik
    -0.12
    workflow
    -0.10
     fox
    -0.09
    wallet
    -0.09
    worksheet
    -0.09
     Warsaw
    -0.09
    .workflow
    -0.09
     circum
    -0.09
     Woodward
    -0.09
    webpack
    -0.09
    POSITIVE LOGITS
     W
    0.26
    W
    0.24
    =W
    0.22
    (W
    0.21
    "W
    0.20
    =w
    0.20
    .w
    0.19
    \tW
    0.18
    .W
    0.18
     w
    0.17
    Activations Density 0.181%

    No Known Activations