© 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. 129624
    Prev
    Next
    INDEX
    Explanations

    prominent travel destinations and related community events

    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
    มà¸ķ
    -0.07
     PURPOSE
    -0.07
    ÑĢÑĥн
    -0.07
    .Ordinal
    -0.07
    plural
    -0.06
    loomberg
    -0.06
    oner
    -0.06
    osta
    -0.06
    üns
    -0.06
    IELD
    -0.06
    POSITIVE LOGITS
     Uncategorized
    0.07
    Corner
    0.07
    raquo
    0.07
    Ưá»
    0.06
     WINAPI
    0.06
    INavigation
    0.06
    .scalablytyped
    0.06
     MetroFramework
    0.06
     Banc
    0.06
    bach
    0.06
    Activations Density 0.022%

    No Known Activations