© 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. 25534
    Prev
    Next
    INDEX
    Explanations

    iPhone 11

    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
     tablet
    -0.14
     Smartphone
    -0.13
     Tablet
    -0.12
    _android
    -0.11
    tablet
    -0.11
     tablets
    -0.10
     Trev
    -0.10
     smartphone
    -0.10
     Grim
    -0.10
     Garn
    -0.10
    POSITIVE LOGITS
     Lightning
    0.15
     Apple
    0.13
     Neural
    0.13
     Face
    0.12
     Pro
    0.12
    .apple
    0.12
     Ceramic
    0.11
     models
    0.11
     Ming
    0.11
     lightning
    0.11
    Activations Density 0.019%

    No Known Activations