© 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. 15-LLAMASCOPE-RES-131K
    11. 87273
    Prev
    Next
    INDEX
    Explanations

    specific websites and URL formats related to ticket sales and travel information

    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
    -FIRST
    -0.07
    enga
    -0.07
    æ¥
    -0.07
    ummer
    -0.06
    ová
    -0.06
    partment
    -0.06
    ÃľM
    -0.06
    encia
    -0.06
    ervers
    -0.06
    chet
    -0.06
    POSITIVE LOGITS
    .com
    0.10
    .io
    0.08
    .co
    0.07
    .org
    0.07
    174
    0.07
    .eu
    0.06
    .ru
    0.06
     заб
    0.06
     slap
    0.06
     eclipse
    0.06
    Activations Density 0.013%

    No Known Activations