© 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. 108721
    Prev
    Next
    INDEX
    Explanations

    accommodations and amenities related to hotel and lodging experiences

    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
    berger
    -0.06
    odata
    -0.06
    ãģ¡ãĤĥãĤĵ
    -0.06
    Margins
    -0.06
     grub
    -0.06
    Replacement
    -0.06
    erp
    -0.06
    æĶ¯
    -0.06
     advent
    -0.06
    wo
    -0.06
    POSITIVE LOGITS
    rones
    0.09
     Sharing
    0.08
    oubles
    0.08
     Shared
    0.07
    Ïĩη
    0.07
     rooms
    0.07
     sharing
    0.07
    æ£ĭçīĮ
    0.07
    ewith
    0.07
    ouples
    0.07
    Activations Density 0.016%

    No Known Activations