© 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. 64751
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by abstract nouns

    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
     dissatisfaction
    -0.10
     diss
    -0.09
    оÑĩки
    -0.08
     lic
    -0.08
     things
    -0.08
     ment
    -0.08
    shine
    -0.08
    ÐĴС
    -0.08
    poons
    -0.08
    azon
    -0.08
    POSITIVE LOGITS
     desire
    0.20
     ability
    0.20
     interest
    0.17
     own
    0.17
     attempts
    0.16
     attempt
    0.14
     experiences
    0.14
     Interest
    0.14
     view
    0.13
     eag
    0.13
    Activations Density 0.080%

    No Known Activations