© 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. 89646
    Prev
    Next
    INDEX
    Explanations

    mentions of awards and recognition related to sustainable practices

    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
     subscriber
    -0.07
    gap
    -0.06
    okus
    -0.06
     Undert
    -0.06
     Cruc
    -0.06
    аÑĢÑĩ
    -0.06
    rana
    -0.05
     oyn
    -0.05
    Render
    -0.05
    -widgets
    -0.05
    POSITIVE LOGITS
     booth
    0.09
     Shank
    0.07
    ÑĢÑĸÑĪ
    0.07
     Booth
    0.07
     conference
    0.07
    Æ°Æ¡ng
    0.07
     Conference
    0.07
     trade
    0.07
     Floor
    0.07
    elper
    0.07
    Activations Density 0.006%

    No Known Activations