© 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. 29388
    Prev
    Next
    INDEX
    Explanations

    past participle formation

    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
     Came
    -0.13
     à¤ķहन
    -0.12
    åĩºãģĻ
    -0.12
     underwent
    -0.12
    came
    -0.10
     fell
    -0.10
     à¤ķहत
    -0.10
     became
    -0.10
     grew
    -0.10
    bdb
    -0.09
    POSITIVE LOGITS
     been
    0.30
    been
    0.23
     Been
    0.23
     BEEN
    0.22
    Been
    0.22
     sido
    0.21
    è¿ĩ
    0.21
    izzato
    0.19
    éģİ
    0.17
     été
    0.16
    Activations Density 0.094%

    No Known Activations