© 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. 105869
    Prev
    Next
    INDEX
    Explanations

    phrases evaluating player performance in football

    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
     mie
    -0.07
    лами
    -0.07
    igos
    -0.07
    uess
    -0.07
    WXYZ
    -0.07
    екÑĤ
    -0.07
    º
    -0.07
    fontName
    -0.07
    ÑĢог
    -0.07
    amber
    -0.07
    POSITIVE LOGITS
     talent
    0.07
    aptor
    0.06
     modern
    0.06
     Sab
    0.05
     remar
    0.05
     ren
    0.05
    èģĶ
    0.05
     craft
    0.05
     contemporary
    0.05
     this
    0.05
    Activations Density 0.024%

    No Known Activations