© 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. 31622
    Prev
    Next
    INDEX
    Explanations

    references to gender and equality rights issues

    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
    tvrt
    -0.08
     lesb
    -0.07
    olk
    -0.07
    ιακ
    -0.07
    atest
    -0.07
    usercontent
    -0.07
     WithEvents
    -0.07
     tablesp
    -0.07
    antor
    -0.07
     åī
    -0.07
    POSITIVE LOGITS
     initiative
    0.08
     section
    0.08
     project
    0.07
     Initiative
    0.07
     module
    0.07
     subsection
    0.06
    786
    0.06
     Experts
    0.06
    eron
    0.06
     experts
    0.06
    Activations Density 0.038%

    No Known Activations