© 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. 80758
    Prev
    Next
    INDEX
    Explanations

    performance metrics related to basketball games

    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
    enburg
    -0.07
    skirts
    -0.07
    æĸŃ
    -0.06
    ordum
    -0.06
     Watt
    -0.06
    iske
    -0.06
    ummings
    -0.06
    á»ĵn
    -0.06
    åľ°ä¸ĭ
    -0.06
    orage
    -0.06
    POSITIVE LOGITS
     repe
    0.08
    ç«ĭ
    0.06
     Outer
    0.06
    alias
    0.06
    ivery
    0.06
     wave
    0.06
     balls
    0.06
     zbo
    0.06
    nds
    0.06
    eto
    0.06
    Activations Density 0.012%

    No Known Activations