© 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. 2102
    Prev
    Next
    INDEX
    Explanations

    questions about Islam

    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
     jihadist
    -0.14
     mosque
    -0.12
     Sheikh
    -0.12
     jih
    -0.12
     Mosque
    -0.11
     Jihad
    -0.11
     quint
    -0.11
     racist
    -0.10
     mosques
    -0.09
     Imam
    -0.09
    POSITIVE LOGITS
     conservative
    0.17
     Wah
    0.14
     hij
    0.13
    ocratic
    0.12
     zak
    0.12
     medieval
    0.12
     hud
    0.11
     Theo
    0.11
    ston
    0.11
     Hud
    0.11
    Activations Density 0.035%

    No Known Activations