© 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. 9-LLAMASCOPE-RES-131K
    11. 95081
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and player selections

    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
    .signals
    -0.07
    ανά
    -0.07
    讯
    -0.07
    arken
    -0.07
    ÑĸнÑĮ
    -0.07
     ì¤Ģ
    -0.07
    AndView
    -0.07
    assi
    -0.07
    ocal
    -0.07
     é«
    -0.07
    POSITIVE LOGITS
    лем
    0.07
    tec
    0.06
    orda
    0.06
    ABL
    0.06
     EV
    0.06
     Tec
    0.06
     shot
    0.06
     GANG
    0.06
     aging
    0.06
    agues
    0.06
    Activations Density 0.499%

    No Known Activations