© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 22143
    Prev
    Next
    INDEX
    Explanations

    using the scientific method

    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
     handwriting
    -0.09
     matching
    -0.09
    oya
    -0.09
     intrigue
    -0.09
     dice
    -0.08
     colourful
    -0.08
     feather
    -0.08
     شر
    -0.08
     unde
    -0.08
    227
    -0.08
    POSITIVE LOGITS
     deco
    0.11
     exhaust
    0.11
    殿
    0.11
     DIST
    0.10
     skinny
    0.10
     Exhaust
    0.10
    ä¸īä¸ī
    0.10
     crunchy
    0.09
    obs
    0.09
     splits
    0.09
    Activations Density 0.019%

    No Known Activations