© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 41390
    Prev
    Next
    INDEX
    Explanations

    important passages and stories

    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
     scripture
    -0.14
     scriptures
    -0.11
     Scripture
    -0.10
     bible
    -0.10
     proclamation
    -0.09
     pigeon
    -0.09
     Scriptures
    -0.09
    Scripts
    -0.09
    agara
    -0.09
    ovich
    -0.09
    POSITIVE LOGITS
     teaching
    0.12
     teach
    0.12
     comfort
    0.11
     passages
    0.11
     fo
    0.11
    warnings
    0.11
     passage
    0.11
     recorded
    0.10
     recording
    0.10
     teaches
    0.10
    Activations Density 0.058%

    No Known Activations