© 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. 5846
    Prev
    Next
    INDEX
    Explanations

    references to groups and organizations in various contexts

    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
    871
    -0.06
    ande
    -0.06
    atur
    -0.06
    ège
    -0.06
    ril
    -0.06
    WithContext
    -0.06
    ivel
    -0.06
    tx
    -0.06
    261
    -0.06
    anca
    -0.06
    POSITIVE LOGITS
     tá»ķ
    0.07
    zano
    0.07
    Ư
    0.06
     глÑĥ
    0.06
    ÑĤÑı
    0.06
    è²¼
    0.06
    RAD
    0.06
    ắm
    0.06
    "@
    0.06
     etm
    0.06
    Activations Density 0.001%

    No Known Activations