© 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. 125226
    Prev
    Next
    INDEX
    Explanations

    numerical relationships and comparisons in data analysis

    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
     Tal
    -0.07
    steder
    -0.06
    ÑĢим
    -0.06
    argin
    -0.06
    718
    -0.06
    ieme
    -0.06
    extras
    -0.06
    ÑĢоÑī
    -0.06
    .margin
    -0.06
    .Version
    -0.05
    POSITIVE LOGITS
     value
    0.09
     знаÑĩение
    0.07
    .mybatisplus
    0.07
    åĢ¤
    0.07
    Å¡i
    0.07
    isposable
    0.07
    erial
    0.07
    athi
    0.07
    .setCellValue
    0.07
    value
    0.06
    Activations Density 0.076%

    No Known Activations