© 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. 11900
    Prev
    Next
    INDEX
    Explanations

    refrigerator or fridge

    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
     heated
    -0.11
     heaters
    -0.09
     Fireplace
    -0.09
    ãĥĹãĥ¬
    -0.09
     heater
    -0.09
    ãĥ¬ãĤ¹
    -0.09
     heats
    -0.09
     Barker
    -0.09
     boiled
    -0.09
     dried
    -0.09
    POSITIVE LOGITS
     refrigerator
    0.33
     fridge
    0.32
     ÑħолодилÑĮ
    0.31
     refriger
    0.28
     Refriger
    0.27
     refr
    0.21
     Frid
    0.21
     tủ
    0.20
    åĨ°
    0.18
     ice
    0.18
    Activations Density 0.055%

    No Known Activations