© 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. 108729
    Prev
    Next
    INDEX
    Explanations

    expressions related to competition and drama in sports

    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
    eteria
    -0.07
    agli
    -0.07
    üh
    -0.07
     demir
    -0.06
    olib
    -0.06
    428
    -0.06
    ÑģÑĤи
    -0.06
    ibbon
    -0.06
    ornings
    -0.05
    birthdate
    -0.05
    POSITIVE LOGITS
    usp
    0.07
     ydk
    0.07
    ppe
    0.07
    rzy
    0.07
     coverage
    0.07
     viewers
    0.07
    coverage
    0.07
     excitement
    0.07
    pk
    0.07
     viewer
    0.07
    Activations Density 0.028%

    No Known Activations