© 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 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. 59236
    Prev
    Next
    INDEX
    Explanations

    references to offline functionality and data management

    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
    æķ·
    -0.07
    ewe
    -0.07
     dijital
    -0.07
    елеÑĦ
    -0.07
    TEL
    -0.07
    aal
    -0.07
     Bour
    -0.07
    floating
    -0.06
     ÙĪاج
    -0.06
    arak
    -0.06
    POSITIVE LOGITS
     offline
    0.18
     Offline
    0.16
    Offline
    0.16
    offline
    0.15
     locally
    0.10
     local
    0.09
     disconnected
    0.08
    离
    0.08
     Local
    0.08
     off
    0.07
    Activations Density 0.006%

    No Known Activations