© 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. 103378
    Prev
    Next
    INDEX
    Explanations

    connections to various forms of engagement and collaboration

    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
    quier
    -0.07
     spect
    -0.06
    جÙĪ
    -0.06
    cia
    -0.06
    askell
    -0.06
    ÑĪел
    -0.06
    ÛĮدÙĩ
    -0.06
    ÑĪев
    -0.06
    oya
    -0.06
    ÑĢован
    -0.06
    POSITIVE LOGITS
    /functions
    0.07
    hip
    0.07
     æ´»
    0.07
    /testing
    0.06
    InParameter
    0.06
     RedirectTo
    0.06
    594
    0.06
    าม
    0.06
    igram
    0.06
    GMEM
    0.06
    Activations Density 0.024%

    No Known Activations