© 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. 80814
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to gameplay mechanics and player rewards

    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
    azu
    -0.08
    ³»
    -0.08
    ÑĢог
    -0.07
    uti
    -0.07
     ayrıca
    -0.07
    utut
    -0.07
     erotik
    -0.07
    ÑıÑĩи
    -0.07
    hek
    -0.07
    vvm
    -0.07
    POSITIVE LOGITS
     certain
    0.07
     literally
    0.07
     extra
    0.07
     non
    0.06
     Extra
    0.06
     “
    0.06
     pre
    0.06
    ëıĮ
    0.06
     various
    0.06
     five
    0.06
    Activations Density 0.042%

    No Known Activations