© 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. 18643
    Prev
    Next
    INDEX
    Explanations

    references to organizations, particularly foundations

    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
     forControlEvents
    -0.07
    argo
    -0.07
    colo
    -0.06
    ask
    -0.06
    tempt
    -0.06
    illion
    -0.06
    agues
    -0.06
    gh
    -0.05
    -es
    -0.05
     blind
    -0.05
    POSITIVE LOGITS
    /Foundation
    0.08
    ãĥ¼ãĥģ
    0.07
    ç½ijåĿĢ
    0.07
    .pa
    0.07
    Ñıви
    0.07
    ायद
    0.07
    .snap
    0.07
     Cummings
    0.07
     Spinner
    0.06
    дÑı
    0.06
    Activations Density 0.000%

    No Known Activations