© 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. 85989
    Prev
    Next
    INDEX
    Explanations

    terms related to contracts and player negotiations 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
    abaj
    -0.07
    ibri
    -0.07
    ë¹ł
    -0.07
    \API
    -0.07
    íĶ½
    -0.07
    liš
    -0.07
    ierz
    -0.06
    rips
    -0.06
    arkin
    -0.06
    pector
    -0.06
    POSITIVE LOGITS
     Tet
    0.06
     extension
    0.06
     Carrier
    0.06
    _extension
    0.06
     corner
    0.06
     Stout
    0.06
    ãĤ
    0.06
     Blo
    0.06
     Facilities
    0.06
     contract
    0.05
    Activations Density 0.170%

    No Known Activations