© 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. 20443
    Prev
    Next
    INDEX
    Explanations

    for use or consumption

    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
    outil
    -0.10
    PageRoute
    -0.09
    /us
    -0.09
    enga
    -0.08
     Enhancement
    -0.08
     accesses
    -0.08
    406
    -0.08
     æĭĽ
    -0.08
     Us
    -0.08
     Improvement
    -0.08
    POSITIVE LOGITS
     use
    0.42
    use
    0.26
     Use
    0.22
     consumption
    0.22
    .use
    0.21
     gebruik
    0.21
     uso
    0.20
    Use
    0.20
     sale
    0.19
     usage
    0.19
    Activations Density 0.076%

    No Known Activations