© 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. 34447
    Prev
    Next
    INDEX
    Explanations

    mantras, visualizations, and practices

    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
     spirituality
    -0.13
     rites
    -0.11
     Kendall
    -0.10
     religion
    -0.10
     zen
    -0.10
     spiritual
    -0.10
     Spiritual
    -0.09
    caster
    -0.09
     Buddhism
    -0.09
     Buddha
    -0.09
    POSITIVE LOGITS
     mantra
    0.13
     Mandal
    0.13
     visualization
    0.13
     rec
    0.12
     med
    0.12
     sig
    0.11
    med
    0.11
     breath
    0.11
     mud
    0.11
    sig
    0.11
    Activations Density 0.037%

    No Known Activations