© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 69028
    Prev
    Next
    INDEX
    Explanations

    instances of the word "give" and its variations, indicating themes of generosity and offering

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    trace
    -0.06
    639
    -0.06
     trace
    -0.06
    762
    -0.06
    sters
    -0.06
    ive
    -0.06
    273
    -0.06
     Trace
    -0.05
    ced
    -0.05
    lico
    -0.05
    POSITIVE LOGITS
    ÑĥлÑĮ
    0.07
     opportunity
    0.07
    ichten
    0.07
     Bylo
    0.06
     Gund
    0.06
    uls
    0.06
    ALLENG
    0.06
    ãĤ¥
    0.06
    æľºä¼ļ
    0.06
    JC
    0.06
    Activations Density 0.019%

    No Known Activations