© 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. 17611
    Prev
    Next
    INDEX
    Explanations

    a chemical company

    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
    ATTRIBUTE
    -0.09
    etz
    -0.09
     Univers
    -0.09
    eru
    -0.09
    IEL
    -0.09
     univers
    -0.09
     weap
    -0.09
     Compact
    -0.09
     CFL
    -0.08
    åĮ
    -0.08
    POSITIVE LOGITS
     US
    0.24
     USA
    0.24
     American
    0.22
    USA
    0.20
    US
    0.20
     Americans
    0.20
    ç¾İåĽ½
    0.19
     ç¾İåĽ½
    0.19
     СШÐIJ
    0.19
    ç¾İåľĭ
    0.18
    Activations Density 0.222%

    No Known Activations