© 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. 42675
    Prev
    Next
    INDEX
    Explanations

    references to controversial or sensitive social issues involving Islam and its critics

    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
     Anast
    -0.07
    heit
    -0.06
     Zionist
    -0.06
    iou
    -0.06
     Lesbian
    -0.06
     anarchist
    -0.06
    ubu
    -0.06
    corn
    -0.06
     Squ
    -0.06
    086
    -0.06
    POSITIVE LOGITS
    ãĤ·ãĥ£ãĥ«
    0.07
     Western
    0.07
     Europe
    0.07
    acks
    0.06
    /extensions
    0.06
     moderate
    0.06
    Europe
    0.06
     svÄĽ
    0.06
     conversions
    0.06
    plib
    0.06
    Activations Density 0.144%

    No Known Activations