© 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. 60612
    Prev
    Next
    INDEX
    Explanations

    heated to make pliable

    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
     cold
    -0.13
     Refriger
    -0.13
     refriger
    -0.13
     ice
    -0.12
    cold
    -0.12
     freezing
    -0.12
    Cold
    -0.12
     Cold
    -0.11
     colder
    -0.11
     hypers
    -0.11
    POSITIVE LOGITS
     heat
    0.17
     temperatures
    0.16
     firing
    0.14
     calc
    0.14
     py
    0.14
    Heat
    0.13
    heat
    0.13
     Heat
    0.13
     decomposition
    0.13
     hot
    0.13
    Activations Density 0.037%

    No Known Activations