© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1892
    Prev
    Next
    INDEX
    Explanations

    elements related to gaming rewards and updates

    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
    ActionCreators
    -0.08
    á»ij
    -0.07
    awah
    -0.07
    gii
    -0.07
    stops
    -0.07
    berg
    -0.07
    WXYZ
    -0.07
    ITERAL
    -0.07
    osals
    -0.07
    osa
    -0.07
    POSITIVE LOGITS
     exclusive
    0.06
     skins
    0.06
     extra
    0.06
    ACS
    0.06
     characters
    0.06
     ÙħÙĥ
    0.06
    exclusive
    0.06
     premium
    0.06
     special
    0.06
     additional
    0.06
    Activations Density 0.012%

    No Known Activations