© 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. 38215
    Prev
    Next
    INDEX
    Explanations

    key concepts related to social and political issues, particularly those affecting marginalized groups and systemic inequalities

    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
    aney
    -0.08
    /gui
    -0.08
    upo
    -0.07
    rouch
    -0.07
    lop
    -0.07
    uco
    -0.07
    ë§Īëĭ¤
    -0.07
     å¾ĴæŃ©
    -0.07
    aucoup
    -0.07
    .Apis
    -0.06
    POSITIVE LOGITS
     may
    0.09
     might
    0.08
     wasn
    0.07
     certainly
    0.07
     should
    0.07
     could
    0.07
     however
    0.06
    ambre
    0.06
     seem
    0.06
     doesn
    0.06
    Activations Density 0.086%

    No Known Activations