© 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. 2088
    Prev
    Next
    INDEX
    Explanations

    managing waste practices

    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
     recycl
    -0.10
     explo
    -0.09
    人æīį
    -0.09
     Stitch
    -0.09
     wastewater
    -0.09
     mux
    -0.08
     Realt
    -0.08
     launder
    -0.08
     sewage
    -0.08
    ollo
    -0.08
    POSITIVE LOGITS
     sorting
    0.18
     circular
    0.16
     sorted
    0.15
     collection
    0.15
     valor
    0.14
     bin
    0.14
    sorted
    0.14
     Sorted
    0.14
     Zero
    0.14
    Circular
    0.13
    Activations Density 0.046%

    No Known Activations