© 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. 14791
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports, competitions, and notable figures within sporting contexts

    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
    onda
    -0.08
    adol
    -0.06
     dominance
    -0.06
    ooled
    -0.06
    uddenly
    -0.06
    afx
    -0.06
    appen
    -0.06
     McCorm
    -0.06
     treff
    -0.06
     üzer
    -0.05
    POSITIVE LOGITS
     among
    0.21
     amongst
    0.19
    among
    0.19
    ä¹ĭä¸Ģ
    0.18
     Among
    0.17
    Among
    0.16
     salah
    0.15
     one
    0.15
     ÛĮÚ©ÛĮ
    0.15
     ÑģÑĢеди
    0.12
    Activations Density 0.047%

    No Known Activations