© 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 EvalsExportsAPI 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. 16527
    Prev
    Next
    INDEX
    Explanations

    discourse related to team dynamics and player evaluations in sports

    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
    izzo
    -0.07
    aida
    -0.07
     <![
    -0.07
     kinds
    -0.07
    óm
    -0.06
    amos
    -0.06
    ascript
    -0.06
    llu
    -0.06
    iez
    -0.06
    ylland
    -0.06
    POSITIVE LOGITS
    æ³ķ人
    0.06
    onga
    0.06
    ==>
    0.06
     zbo
    0.06
     selv
    0.06
     bán
    0.06
    VERR
    0.06
     overrun
    0.06
     ëĤ´ëł¤
    0.06
     æij
    0.06
    Activations Density 0.007%

    No Known Activations