© 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. 80659
    Prev
    Next
    INDEX
    Explanations

    references to player statistics and historical achievements in basketball

    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
    indr
    -0.07
    æ§
    -0.07
    andin
    -0.07
    iosis
    -0.07
    unner
    -0.07
    izon
    -0.07
    eldorf
    -0.06
    croft
    -0.06
    reste
    -0.06
    orca
    -0.06
    POSITIVE LOGITS
     ever
    0.09
     person
    0.07
     HISTORY
    0.07
     Gros
    0.07
    -ever
    0.07
     dual
    0.07
     persons
    0.06
     Ever
    0.06
     Persons
    0.06
    Dual
    0.06
    Activations Density 0.009%

    No Known Activations