© 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. 45298
    Prev
    Next
    INDEX
    Explanations

    five parts

    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
    folk
    -0.09
     Dietary
    -0.09
     ath
    -0.09
     Gallagher
    -0.09
     Fischer
    -0.09
    ñana
    -0.09
    Łèĥ½
    -0.08
     craw
    -0.08
    ãĢĥ
    -0.08
    Pu
    -0.08
    POSITIVE LOGITS
     incre
    0.24
     GL
    0.21
    GL
    0.17
     sat
    0.14
    /GL
    0.14
     Gl
    0.13
    ,GL
    0.13
     Vict
    0.13
     gluc
    0.12
     meal
    0.12
    Activations Density 0.017%

    No Known Activations