© 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. 96414
    Prev
    Next
    INDEX
    Explanations

    references to data structures and their properties

    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
    ساÙĨ
    -0.07
     proxy
    -0.07
    _PROXY
    -0.06
    proxy
    -0.06
    .proxy
    -0.06
    лÑĸд
    -0.06
    zi
    -0.06
     vo
    -0.06
    sla
    -0.06
    loub
    -0.06
    POSITIVE LOGITS
    ména
    0.06
    ãĤ¢ãĥ¼
    0.06
    arker
    0.06
    ierz
    0.06
    UrlParser
    0.06
     Og
    0.06
    oron
    0.06
     Weg
    0.06
    929
    0.06
    Å¡ov
    0.06
    Activations Density 0.051%

    No Known Activations