© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 3267
    Prev
    Next
    INDEX
    Explanations

    avoid phthalates

    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
     toxin
    -0.11
    Neutral
    -0.10
     Neutral
    -0.10
    -neutral
    -0.09
     contaminated
    -0.09
     neutral
    -0.09
    ControlItem
    -0.09
    olesterol
    -0.09
    ollen
    -0.08
    remen
    -0.08
    POSITIVE LOGITS
     chemicals
    0.20
     ingredients
    0.20
     chemical
    0.17
     formal
    0.16
    chemical
    0.15
     Formal
    0.15
     ingredient
    0.15
     banned
    0.15
     harsh
    0.14
     Mercury
    0.14
    Activations Density 0.087%

    No Known Activations