© 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. 29329
    Prev
    Next
    INDEX
    Explanations

    wildfire smoke detection

    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
     storm
    -0.11
     Hurricane
    -0.11
     hurricane
    -0.10
    Splash
    -0.10
     storms
    -0.10
     floods
    -0.10
     Tek
    -0.10
    æ½®
    -0.10
     stormed
    -0.10
     Blast
    -0.09
    POSITIVE LOGITS
     fire
    0.18
     brush
    0.18
     Fire
    0.18
     burn
    0.16
     smoke
    0.16
    çĥ§
    0.15
     burned
    0.15
     pož
    0.14
     forest
    0.14
    fire
    0.14
    Activations Density 0.022%

    No Known Activations