© 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. 9-LLAMASCOPE-RES-131K
    11. 99279
    Prev
    Next
    INDEX
    Explanations

    references to socio-economic concerns or measures affecting specific communities

    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
    ocard
    -0.07
    ãĥ¼ãĥª
    -0.07
    grave
    -0.06
     Tavern
    -0.06
     rehe
    -0.06
     grave
    -0.06
     lorem
    -0.06
    emoc
    -0.06
    .fm
    -0.06
     solidity
    -0.06
    POSITIVE LOGITS
    asse
    0.07
    å¡
    0.07
    iem
    0.07
    rne
    0.07
    avel
    0.07
    olta
    0.07
    arge
    0.06
     ÙģرÙĪدگاÙĩ
    0.06
    orz
    0.06
     Kle
    0.06
    Activations Density 0.072%

    No Known Activations