© 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. 12907
    Prev
    Next
    INDEX
    Explanations

    words starting with de-

    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
    /*č\n
    -0.10
     pro
    -0.10
    aliz
    -0.10
     ell
    -0.09
    ainted
    -0.09
    arrants
    -0.09
     rud
    -0.09
    -wsj
    -0.09
    ardu
    -0.09
     Buk
    -0.09
    POSITIVE LOGITS
     bunk
    0.11
    elopment
    0.10
     de
    0.10
    unk
    0.10
    ict
    0.10
    ader
    0.10
    µľ
    0.10
     Colo
    0.10
     novo
    0.10
     facto
    0.09
    Activations Density 0.042%

    No Known Activations