© 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. 5915
    Prev
    Next
    INDEX
    Explanations

    concepts related to community guidelines and social 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
    WithOptions
    -0.07
     Zug
    -0.06
     unconventional
    -0.06
    erte
    -0.06
     Bon
    -0.06
    ème
    -0.05
     poly
    -0.05
     size
    -0.05
    ouce
    -0.05
     catast
    -0.05
    POSITIVE LOGITS
    heck
    0.09
     racism
    0.09
    INFRINGEMENT
    0.08
    /tos
    0.08
     ethnic
    0.08
    upt
    0.07
     racist
    0.07
    اÙĪÙĨد
    0.07
     Subway
    0.07
    rac
    0.07
    Activations Density 0.002%

    No Known Activations