© 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. 10085
    Prev
    Next
    INDEX
    Explanations

    determiner possessive pronoun article noun

    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
     alive
    -0.11
     chtÄĽ
    -0.09
     marvel
    -0.09
     Dawn
    -0.09
     nice
    -0.09
     rel
    -0.09
    ĽĦ
    -0.08
    £p
    -0.08
    езÑĥлÑĮÑĤ
    -0.08
    åł¡
    -0.08
    POSITIVE LOGITS
    wat
    0.11
    izable
    0.09
     wat
    0.09
    ＼＼
    0.09
     ent
    0.09
    ural
    0.08
     inter
    0.08
     mot
    0.08
     sud
    0.08
     inner
    0.08
    Activations Density 0.164%

    No Known Activations