© 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. 26991
    Prev
    Next
    INDEX
    Explanations

    instances of gratitude and appreciation for shared content

    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
    nam
    -0.08
     cor
    -0.06
    iy
    -0.06
    Nam
    -0.06
     Nam
    -0.06
    lish
    -0.06
    ra
    -0.06
    ainer
    -0.05
    bay
    -0.05
    aph
    -0.05
    POSITIVE LOGITS
    )((((
    0.07
    981
    0.07
    è¿Ļä¹Ī
    0.07
    AZY
    0.07
    Ĵáŀ
    0.07
     ç¥
    0.07
     minh
    0.07
    arie
    0.07
    CHED
    0.07
    à¥Īत
    0.07
    Activations Density 0.004%

    No Known Activations