© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 45070
    Prev
    Next
    INDEX
    Explanations

    providing sustenance

    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
     compens
    -0.10
     Frog
    -0.09
     profits
    -0.09
     riches
    -0.09
    nyder
    -0.09
     compensated
    -0.09
    usk
    -0.08
    /LICENSE
    -0.08
     Restore
    -0.08
     Wein
    -0.08
    POSITIVE LOGITS
     subs
    0.30
     bread
    0.25
    subs
    0.22
    bread
    0.21
     Bread
    0.19
     bills
    0.17
     ends
    0.17
     provider
    0.16
     support
    0.16
     sust
    0.16
    Activations Density 0.094%

    No Known Activations