© 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. 60474
    Prev
    Next
    INDEX
    Explanations

    descriptions of artistic communities and their supportive nature

    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
    itele
    -0.07
    plan
    -0.07
    ouz
    -0.07
    bz
    -0.06
    باÙĨ
    -0.06
     Capac
    -0.06
     hit
    -0.06
    lobe
    -0.06
    ón
    -0.06
     sn
    -0.06
    POSITIVE LOGITS
     resources
    0.08
     access
    0.07
     dostup
    0.07
     opportunities
    0.07
    -network
    0.07
     NSStringFromClass
    0.07
     mạng
    0.07
     availability
    0.07
     network
    0.07
    à¹ģหล
    0.07
    Activations Density 0.026%

    No Known Activations