© 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. 64703
    Prev
    Next
    INDEX
    Explanations

    she followed by verb

    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
     himself
    -0.13
     seul
    -0.13
     завиÑģим
    -0.13
    so
    -0.12
    妻
    -0.12
    ustil
    -0.10
     koje
    -0.10
     vzdálen
    -0.10
     должен
    -0.09
    žil
    -0.09
    POSITIVE LOGITS
     herself
    0.51
    pher
    0.26
    athed
    0.26
     hers
    0.25
     her
    0.24
    -même
    0.22
    /he
    0.22
    athing
    0.21
    editary
    0.21
    ila
    0.21
    Activations Density 0.135%

    No Known Activations