© 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. 47167
    Prev
    Next
    INDEX
    Explanations

    humidity and temperature ranges

    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
     jungle
    -0.15
     Jungle
    -0.14
     jung
    -0.10
     lush
    -0.10
     hors
    -0.10
     redund
    -0.10
    isiyle
    -0.09
     Rahman
    -0.09
     rich
    -0.09
     rice
    -0.09
    POSITIVE LOGITS
     dry
    0.27
     desert
    0.24
     drought
    0.23
     Desert
    0.21
    dry
    0.21
     Dry
    0.21
    Dry
    0.20
     khô
    0.18
     ÑģÑĥÑħ
    0.17
     Mediterranean
    0.16
    Activations Density 0.059%

    No Known Activations