© 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. 18596
    Prev
    Next
    INDEX
    Explanations

    possessive related to others

    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
    èĩªå·±çļĦ
    -0.10
    798
    -0.09
    indir
    -0.09
    htar
    -0.08
    518
    -0.08
    áºŃn
    -0.08
    人æ°Ĺ
    -0.08
    è¢ĸ
    -0.08
    894
    -0.08
     herself
    -0.08
    POSITIVE LOGITS
     respective
    0.18
     bodies
    0.15
     company
    0.13
    ÂĢÂĻ
    0.12
     else
    0.12
    '
    0.12
     lives
    0.12
    /company
    0.12
     differences
    0.11
    odies
    0.11
    Activations Density 0.005%

    No Known Activations