© 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. 50830
    Prev
    Next
    INDEX
    Explanations

    Quranic revelations

    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
     Stuart
    -0.11
     Christ
    -0.11
     Imam
    -0.11
     Sheikh
    -0.11
     Mosque
    -0.11
     Hasan
    -0.10
     Hero
    -0.10
     Sultan
    -0.10
     Mahmoud
    -0.10
     pap
    -0.10
    POSITIVE LOGITS
     revelations
    0.14
     sur
    0.13
     Buk
    0.13
     rec
    0.13
     Sur
    0.13
     Hud
    0.12
     Mush
    0.12
     Kare
    0.12
    /ay
    0.11
     revelation
    0.11
    Activations Density 0.044%

    No Known Activations