© 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. 95946
    Prev
    Next
    INDEX
    Explanations

    references to religious sites and associated rituals or festivals

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    antium
    -0.08
    éal
    -0.07
    dorf
    -0.07
    asers
    -0.07
    angelo
    -0.07
    ertas
    -0.07
    uum
    -0.07
     кÑĥ
    -0.06
     cá»ij
    -0.06
    ampa
    -0.06
    POSITIVE LOGITS
     dedication
    0.09
     cult
    0.08
     dedic
    0.08
     patron
    0.08
     shrine
    0.08
     shr
    0.07
    wor
    0.07
     devotion
    0.07
     dedicate
    0.07
     vot
    0.07
    Activations Density 0.107%

    No Known Activations