© 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. 26870
    Prev
    Next
    INDEX
    Explanations

    rules and regulations related to sports gameplay and procedures

    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
     Steering
    -0.06
    dej
    -0.06
    ritz
    -0.06
    ?><
    -0.06
    253
    -0.06
    é«ĺ度
    -0.06
    832
    -0.06
    ekler
    -0.06
     pulse
    -0.06
    ilter
    -0.06
    POSITIVE LOGITS
     fou
    0.08
     Pars
    0.07
    ÑģÑı
    0.07
     foul
    0.07
     Rule
    0.06
    Rule
    0.06
     counts
    0.06
    cd
    0.06
    -stop
    0.06
    posable
    0.06
    Activations Density 0.008%

    No Known Activations