© 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. 2143
    Prev
    Next
    INDEX
    Explanations

    substance, material, or compound

    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
    otland
    -0.09
    atron
    -0.09
    įng
    -0.08
    ÙĪÛĮÙĨت
    -0.08
     ï¾ī
    -0.08
     recip
    -0.08
     -*-č\n
    -0.08
     ï¾į
    -0.08
     Verfüg
    -0.08
    fsp
    -0.07
    POSITIVE LOGITS
     substance
    0.30
     stuff
    0.28
     Stuff
    0.21
    stuff
    0.21
     material
    0.20
     product
    0.20
     Substance
    0.20
     agent
    0.19
    Stuff
    0.18
     compound
    0.17
    Activations Density 0.029%

    No Known Activations