© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 107933
    Prev
    Next
    INDEX
    Explanations

    references to names or terms from sports and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    roat
    -0.06
    omet
    -0.06
     Yates
    -0.06
    âĪ
    -0.06
    viÄį
    -0.05
     ogr
    -0.05
    mp
    -0.05
    uby
    -0.05
    rique
    -0.05
     równ
    -0.05
    POSITIVE LOGITS
    tube
    0.07
    ãĤº
    0.07
    leneck
    0.07
    eah
    0.07
    ĵåIJį
    0.07
     Å¡Å¥
    0.06
    åĬ¨çĶŁæĪIJ
    0.06
    "./
    0.06
    ye
    0.06
    ằm
    0.06
    Activations Density 0.027%

    No Known Activations