© 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. 53813
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Alexandria Ocasio-Cortez."

    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
    SEA
    -0.07
    ogan
    -0.07
    اÙħÙĩ
    -0.06
    alach
    -0.06
    anga
    -0.06
    tiv
    -0.06
     Kare
    -0.06
    æ³ķ人
    -0.06
    Äĥr
    -0.06
    ixon
    -0.06
    POSITIVE LOGITS
    ectl
    0.07
     Cong
    0.06
    çīĽ
    0.06
     DEM
    0.06
     ADS
    0.06
    isms
    0.06
    ephir
    0.06
    Ãły
    0.06
     dém
    0.06
    اÙĬر
    0.06
    Activations Density 0.001%

    No Known Activations