© 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. 128096
    Prev
    Next
    INDEX
    Explanations

    references to baseball positions and field areas

    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
    497
    -0.07
    essel
    -0.06
    onga
    -0.06
     newInstance
    -0.06
    429
    -0.06
    oldt
    -0.06
    832
    -0.05
    ,
    -0.05
     group
    -0.05
     roster
    -0.05
    POSITIVE LOGITS
    ITOR
    0.07
    inder
    0.07
    .Microsoft
    0.07
    .FieldName
    0.07
     ÑĪи
    0.07
    INDER
    0.07
    ÑĢÑĥÑĩ
    0.07
    YPD
    0.07
    ARED
    0.07
     Field
    0.07
    Activations Density 0.006%

    No Known Activations