© 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. 29848
    Prev
    Next
    INDEX
    Explanations

    based on religious

    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
    hta
    -0.09
    quate
    -0.09
    -directed
    -0.09
    eah
    -0.09
     reflected
    -0.08
     Beard
    -0.08
     instantiation
    -0.08
     fraught
    -0.08
     Rounded
    -0.08
    -Owned
    -0.08
    POSITIVE LOGITS
     based
    0.38
    åŁºäºİ
    0.30
     Based
    0.29
     dá»±a
    0.27
    based
    0.27
    Based
    0.25
     bas
    0.21
    _based
    0.19
     tied
    0.18
     BASE
    0.17
    Activations Density 0.347%

    No Known Activations