© 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. 14931
    Prev
    Next
    INDEX
    Explanations

    english sentence lists

    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
     linguistic
    -0.10
     ngôn
    -0.10
    ãĢģãĢģ
    -0.10
    iverse
    -0.09
     chiế
    -0.09
     gramm
    -0.09
     languages
    -0.09
     LATIN
    -0.09
    strap
    -0.09
     dialect
    -0.09
    POSITIVE LOGITS
    IEL
    0.15
     Native
    0.14
     Cambridge
    0.14
     native
    0.13
     English
    0.13
    iel
    0.13
     idi
    0.12
     British
    0.12
    Native
    0.12
    English
    0.12
    Activations Density 0.193%

    No Known Activations