© 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. 77820
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and functions related to network socket programming

    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
    isp
    -0.07
     ÄĮer
    -0.07
    anja
    -0.07
    Äįas
    -0.06
    .jsoup
    -0.06
    ãĥijãĥ³
    -0.06
     Sutton
    -0.06
     unreachable
    -0.06
    sı
    -0.06
     Heading
    -0.06
    POSITIVE LOGITS
     transport
    0.08
     port
    0.08
     peer
    0.07
     listen
    0.07
     Peer
    0.07
     Transport
    0.07
    Peer
    0.07
     channel
    0.07
    pair
    0.07
     transports
    0.07
    Activations Density 0.065%

    No Known Activations