© 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. 40420
    Prev
    Next
    INDEX
    Explanations

    details about local attractions and experiences in a tourist destination

    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
    ocha
    -0.07
    uez
    -0.06
    ayload
    -0.06
     visible
    -0.06
    ourn
    -0.06
     â
    -0.06
    visible
    -0.06
    unicorn
    -0.05
     Abstract
    -0.05
     -
    -0.05
    POSITIVE LOGITS
     ãĥĬ
    0.07
    	ROM
    0.07
    allen
    0.07
    ythe
    0.07
    Ïģε
    0.07
    isce
    0.07
    akis
    0.07
    enta
    0.07
    kest
    0.07
    celik
    0.07
    Activations Density 0.004%

    No Known Activations