© 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. 94428
    Prev
    Next
    INDEX
    Explanations

    instances of media and social actions related to celebrity events and interactions

    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
    æĮĤ
    -0.07
    äch
    -0.07
    æķ
    -0.07
    اÙĦÙĩ
    -0.07
    opup
    -0.07
    меÑĩ
    -0.07
    олаг
    -0.07
    ESA
    -0.07
    AdapterManager
    -0.07
    .uri
    -0.07
    POSITIVE LOGITS
    asl
    0.07
     reaction
    0.06
     fail
    0.06
     antics
    0.06
     reactions
    0.06
    gif
    0.06
     bro
    0.06
     shut
    0.06
     slow
    0.06
     facial
    0.06
    Activations Density 0.041%

    No Known Activations