© 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. 95188
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding artistic disciplines and their intersection with various fields and industries

    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
    ima
    -0.06
    burgh
    -0.06
    ewan
    -0.06
     Courtesy
    -0.05
     meaning
    -0.05
     Shape
    -0.05
     Tear
    -0.05
    fit
    -0.05
     âĪ
    -0.05
     unused
    -0.05
    POSITIVE LOGITS
    osate
    0.08
    ICY
    0.07
    rech
    0.07
    estone
    0.07
    /apis
    0.07
    ymm
    0.07
     profesional
    0.07
    stÃŃ
    0.07
    StandardItem
    0.07
    ارب
    0.07
    Activations Density 0.022%

    No Known Activations