© 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. 5119
    Prev
    Next
    INDEX
    Explanations

    praying over or for requests

    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
     sacred
    -0.10
     Sacred
    -0.10
     sacram
    -0.10
     preaching
    -0.10
    ãĢĥ
    -0.10
     pron
    -0.09
    MSN
    -0.09
     prov
    -0.09
     rites
    -0.09
    pta
    -0.09
    POSITIVE LOGITS
    ç¥
    0.22
     invocation
    0.18
     cầu
    0.17
    Pr
    0.17
    pray
    0.16
     دع
    0.16
     Pr
    0.16
     petition
    0.16
     petitions
    0.16
     pray
    0.15
    Activations Density 0.055%

    No Known Activations