© 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. 15-LLAMASCOPE-RES-131K
    11. 86324
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports performance and player actions

    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
    esti
    -0.07
    isclosed
    -0.07
     Pitch
    -0.07
    lint
    -0.06
     pitch
    -0.06
    pac
    -0.06
    odus
    -0.06
    athi
    -0.06
    chemy
    -0.06
    pitch
    -0.06
    POSITIVE LOGITS
    vik
    0.07
    .createClass
    0.07
    ['__
    0.07
    .fe
    0.07
     dir
    0.07
    ewise
    0.06
    egen
    0.06
     Charge
    0.06
     Roose
    0.06
    .staff
    0.06
    Activations Density 0.006%

    No Known Activations