© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 92308
    Prev
    Next
    INDEX
    Explanations

    network-related protocols and configurations

    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
    rose
    -0.07
    ãĥ¼ãĥĩ
    -0.07
    loat
    -0.07
     CreateTable
    -0.07
     landing
    -0.07
     Welsh
    -0.06
    uida
    -0.06
    ieder
    -0.06
    itches
    -0.06
    Wel
    -0.06
    POSITIVE LOGITS
    _tunnel
    0.08
     Tor
    0.07
     socks
    0.07
    apro
    0.07
    -proxy
    0.07
     transparent
    0.07
    .Proxy
    0.07
     SOCK
    0.07
    proxy
    0.06
     proxies
    0.06
    Activations Density 0.026%

    No Known Activations