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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125476
    Prev
    Next
    INDEX
    Explanations

    descriptions and discussions related to routes and navigation

    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
     ÙģرÙĪد
    -0.07
    _OBJC
    -0.07
    .ColumnHeader
    -0.07
    ãĤ«ãĥ¼
    -0.07
    loor
    -0.07
    inspace
    -0.07
    ntag
    -0.07
    ascade
    -0.07
    izon
    -0.07
    pedia
    -0.07
    POSITIVE LOGITS
     route
    0.14
     routes
    0.12
     bypass
    0.11
    -route
    0.10
     Route
    0.10
    route
    0.09
    Route
    0.09
     circuit
    0.09
     path
    0.09
     indirect
    0.09
    Activations Density 0.045%

    No Known Activations