© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 7883
    Prev
    Next
    INDEX
    Explanations

    packaging, spoons, materials, design

    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
    Negative Logits
    eldo
    -0.09
    å«
    -0.09
    uments
    -0.09
    weapons
    -0.09
     vessel
    -0.08
    _barrier
    -0.08
    atto
    -0.08
    Unmount
    -0.08
    atables
    -0.08
     vessels
    -0.08
    POSITIVE LOGITS
     design
    0.31
     materials
    0.26
    æĿIJæĸĻ
    0.21
     Materials
    0.21
     Design
    0.19
    design
    0.19
    Materials
    0.19
     manufacturing
    0.19
     designs
    0.19
    materials
    0.18
    Activations Density 0.158%

    No Known Activations