© 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. 85023
    Prev
    Next
    INDEX
    Explanations

    references to torrent sites and related file-sharing terminology

    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
    Sdk
    -0.07
    енÑģ
    -0.06
    EDIA
    -0.06
    ãĤ«ãĥ¼
    -0.06
    edia
    -0.06
    iscard
    -0.06
    宾
    -0.06
    ÑĢоÑĪ
    -0.06
    ãĥ©ãĤ¹
    -0.06
    ingo
    -0.06
    POSITIVE LOGITS
    oni
    0.07
     operation
    0.07
     domain
    0.06
     founder
    0.06
     traffic
    0.06
     operating
    0.06
     Operation
    0.06
    erli
    0.06
    ERN
    0.06
     founders
    0.06
    Activations Density 0.001%

    No Known Activations