© 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. 103973
    Prev
    Next
    INDEX
    Explanations

    instances of action and combat in sports contexts

    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
    istrovstvÃŃ
    -0.10
    gewater
    -0.08
    .mods
    -0.08
    agher
    -0.08
    วล
    -0.08
    ncmp
    -0.07
    erah
    -0.07
    ibbon
    -0.07
    mojom
    -0.07
    zzle
    -0.07
    POSITIVE LOGITS
    0.06
     wel
    0.05
     Homework
    0.05
     rings
    0.05
    íĺķ
    0.05
     charge
    0.05
    .Cookies
    0.05
     Clin
    0.05
     initiative
    0.05
     counter
    0.05
    Activations Density 0.001%

    No Known Activations