© 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. 26862
    Prev
    Next
    INDEX
    Explanations

    concepts related to varying perspectives and experiences among individuals or groups

    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
    _OVERRIDE
    -0.07
    ès
    -0.07
    Äįky
    -0.07
    adar
    -0.06
     BÄĽ
    -0.06
    ighton
    -0.06
    ëįķ
    -0.06
    .WebControls
    -0.06
    024
    -0.06
    íĭ´
    -0.06
    POSITIVE LOGITS
     differently
    0.26
     different
    0.23
    different
    0.20
     differ
    0.19
     differs
    0.19
     diferente
    0.19
     Different
    0.18
    ä¸įåIJĮçļĦ
    0.17
     khác
    0.17
    Different
    0.17
    Activations Density 0.066%

    No Known Activations