© 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. 123438
    Prev
    Next
    INDEX
    Explanations

    elements related to diversity and inclusion

    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
    loff
    -0.08
    κή
    -0.07
    anches
    -0.07
    Neo
    -0.07
    trak
    -0.07
    DDL
    -0.06
    OffsetTable
    -0.06
    nea
    -0.06
    addon
    -0.06
    loat
    -0.06
    POSITIVE LOGITS
     voices
    0.10
     competing
    0.09
    çļĦå£°éŁ³
    0.07
     expertise
    0.07
     Voices
    0.07
     sources
    0.07
     interpretation
    0.06
     equally
    0.06
     stakeholders
    0.06
     SOUR
    0.06
    Activations Density 0.033%

    No Known Activations