© 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. 39266
    Prev
    Next
    INDEX
    Explanations

    describing visual elements with context

    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
     dots
    -0.10
    .contents
    -0.10
     knots
    -0.09
     photographs
    -0.09
     pictures
    -0.09
    andan
    -0.09
    ez
    -0.09
    apos
    -0.09
    Contents
    -0.09
     inval
    -0.08
    POSITIVE LOGITS
     background
    0.16
     backgrounds
    0.13
     Background
    0.13
     behind
    0.13
     surrounding
    0.13
    background
    0.12
    èĥĮæĻ¯
    0.12
     surrounds
    0.11
     surround
    0.11
     surroundings
    0.11
    Activations Density 0.069%

    No Known Activations