© 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. 40447
    Prev
    Next
    INDEX
    Explanations

    The main concepts in epistles

    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
     Isaiah
    -0.11
     scriptures
    -0.11
     Exodus
    -0.10
     Scriptures
    -0.10
     Psalm
    -0.10
     scripture
    -0.10
    cken
    -0.10
    azu
    -0.10
     Genesis
    -0.10
    Genesis
    -0.10
    POSITIVE LOGITS
     Paul
    0.38
    Paul
    0.33
     paul
    0.29
     Ep
    0.19
     letter
    0.19
     ep
    0.17
     Corinth
    0.17
     Paulo
    0.17
     Letters
    0.17
     Paula
    0.17
    Activations Density 0.037%

    No Known Activations