© 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. 89815
    Prev
    Next
    INDEX
    Explanations

    names of athletes, primarily focused on football players

    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
    ELLOW
    -0.08
    nock
    -0.07
    :CGRect
    -0.07
    UDGE
    -0.07
    ansom
    -0.07
    Ø´ÙħاÙĦÛĮ
    -0.07
    .vertx
    -0.07
    vang
    -0.07
    pedia
    -0.07
    ÅĻet
    -0.07
    POSITIVE LOGITS
     gele
    0.07
    umn
    0.06
     Mayweather
    0.06
     Shade
    0.06
    jah
    0.06
    443
    0.06
     sper
    0.06
     Laf
    0.06
     Exodus
    0.06
    vious
    0.06
    Activations Density 0.026%

    No Known Activations