© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35253
    Prev
    Next
    INDEX
    Explanations

    npm install, npx create, Node released

    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
     Dispatch
    -0.12
     DISPATCH
    -0.11
    uite
    -0.11
    566
    -0.10
    asy
    -0.10
     FM
    -0.10
     SSA
    -0.09
     dispatch
    -0.09
    dispatch
    -0.09
    .getAs
    -0.09
    POSITIVE LOGITS
    npm
    0.18
     npm
    0.17
     node
    0.16
     Node
    0.16
    (node
    0.15
     Bun
    0.14
    .node
    0.14
    (Node
    0.13
    /node
    0.12
     yarn
    0.12
    Activations Density 0.035%

    No Known Activations