© 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. 87981
    Prev
    Next
    INDEX
    Explanations

    mentions of various sports, particularly football and wrestling

    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
    klad
    -0.07
    born
    -0.06
    ÄĻk
    -0.06
    engkap
    -0.06
     reminder
    -0.06
     Adler
    -0.06
    inki
    -0.06
    alli
    -0.06
    inue
    -0.06
    illard
    -0.06
    POSITIVE LOGITS
     Association
    0.09
    Association
    0.08
     League
    0.08
     Federation
    0.07
     Eag
    0.07
     Associ
    0.07
     DataBase
    0.07
     authDomain
    0.07
    alex
    0.07
    ubic
    0.06
    Activations Density 0.008%

    No Known Activations