© 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. 37789
    Prev
    Next
    INDEX
    Explanations

    pre-made templates

    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
     stro
    -0.10
    implify
    -0.09
    angle
    -0.09
     Wright
    -0.09
     twe
    -0.09
     Kok
    -0.09
    olve
    -0.09
     SPI
    -0.09
    ADM
    -0.08
     Haw
    -0.08
    POSITIVE LOGITS
     drag
    0.18
     templates
    0.18
    templates
    0.15
     template
    0.15
     Drag
    0.15
     Templates
    0.15
     AI
    0.13
    Drag
    0.13
    _templates
    0.12
    Templates
    0.12
    Activations Density 0.091%

    No Known Activations