© 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. 38280
    Prev
    Next
    INDEX
    Explanations

    the presence of key player names and associated quotes or dialogue 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
    enko
    -0.08
    otron
    -0.08
    omen
    -0.07
    foy
    -0.07
    ptime
    -0.07
    odyn
    -0.07
    ást
    -0.07
    олÑĮно
    -0.07
    illez
    -0.07
    irse
    -0.07
    POSITIVE LOGITS
     dead
    0.06
    kaç
    0.06
     Kore
    0.05
     plenty
    0.05
     :]
    0.05
     veto
    0.05
     bur
    0.05
    usa
    0.05
    endor
    0.05
     answered
    0.05
    Activations Density 0.007%

    No Known Activations