© 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. 56252
    Prev
    Next
    INDEX
    Explanations

    dry, drying, evaporation

    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
    otify
    -0.09
     Cooler
    -0.09
    avigate
    -0.09
     buffered
    -0.09
     Buffered
    -0.09
    heimer
    -0.08
    alous
    -0.08
     Lantern
    -0.08
    -fetch
    -0.08
    ШÐIJ
    -0.08
    POSITIVE LOGITS
     drying
    0.25
     dry
    0.22
     Dry
    0.19
     ev
    0.18
     dried
    0.18
    Dry
    0.17
    dry
    0.17
     dryer
    0.16
     khô
    0.16
     vac
    0.16
    Activations Density 0.008%

    No Known Activations