© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 11393
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and determiners

    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
    Negative Logits
    ä¸Ģç§į
    -0.09
     sebuah
    -0.08
     fiat
    -0.08
    OURS
    -0.08
    rane
    -0.08
    ä¸Ģ个人
    -0.08
     имÑĥ
    -0.08
    eroon
    -0.08
     clo
    -0.08
    338
    -0.08
    POSITIVE LOGITS
     their
    0.16
     his
    0.16
     your
    0.16
     svůj
    0.14
     our
    0.13
     ihre
    0.13
     svo
    0.12
     à¤ħपन
    0.12
     své
    0.12
     svého
    0.12
    Activations Density 0.098%

    No Known Activations