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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 94417
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and relationships in the context of sports careers

    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
     Williamson
    -0.08
    ľ
    -0.06
    FML
    -0.06
    GetType
    -0.06
    Seleccione
    -0.06
    orld
    -0.06
    asso
    -0.06
    icom
    -0.06
    dex
    -0.06
    adin
    -0.06
    POSITIVE LOGITS
    ä¼¼
    0.09
    RICT
    0.07
    .WinForms
    0.07
    azers
    0.07
     année
    0.07
    IMA
    0.06
     bystand
    0.06
     vandal
    0.06
    ä¸Ģå¹´
    0.06
    .CustomButton
    0.06
    Activations Density 0.002%

    No Known Activations