© 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. 3057
    Prev
    Next
    INDEX
    Explanations

    mentions of data serialization and related technical concepts

    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
    mith
    -0.07
    igham
    -0.07
    illard
    -0.06
    umber
    -0.06
    egra
    -0.06
    uala
    -0.06
    BarItem
    -0.06
    æł¹
    -0.06
    daÅŁ
    -0.06
    ignment
    -0.06
    POSITIVE LOGITS
    oldur
    0.06
    ogg
    0.06
    ked
    0.06
    ghest
    0.06
    orf
    0.06
     ÄijÃŃch
    0.06
     clearTimeout
    0.06
    éºĹ
    0.06
    ë²Ī
    0.06
    ound
    0.06
    Activations Density 0.001%

    No Known Activations