© 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. 10714
    Prev
    Next
    INDEX
    Explanations

    group bonds and emphasis

    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
     duo
    -0.12
     Duo
    -0.11
     tandem
    -0.11
     dign
    -0.10
     pareja
    -0.10
     beide
    -0.10
     consort
    -0.09
     gangs
    -0.09
     crowds
    -0.09
     armies
    -0.09
    POSITIVE LOGITS
     member
    0.22
     members
    0.22
     group
    0.21
    æĪIJåijĺ
    0.21
     dynamics
    0.21
     leader
    0.20
     Dynamics
    0.18
     chemistry
    0.18
     team
    0.17
    members
    0.17
    Activations Density 0.123%

    No Known Activations