© 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. 15-LLAMASCOPE-RES-131K
    11. 26410
    Prev
    Next
    INDEX
    Explanations

    calls to action related to following social media accounts and engaging with content online

    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
    âĢ¦↵
    -0.09
    âĢ¦
    -0.07
     âĢ¦↵
    -0.07
    ,
    -0.07
    l
    -0.07
    ...↵
    -0.06
    ix
    -0.06
     t
    -0.06
    3
    -0.06
    201
    -0.06
    POSITIVE LOGITS
    ADDE
    0.10
    'gc
    0.10
     nuest
    0.10
     PROCUREMENT
    0.09
     kê
    0.09
     Hüs
    0.09
    .scalablytyped
    0.09
     Mã
    0.09
     nackte
    0.09
     geil
    0.09
    Activations Density 0.007%

    No Known Activations