© 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. 106649
    Prev
    Next
    INDEX
    Explanations

    phrases related to purchasing and transactions

    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
    å¯Ł
    -0.07
    ë¹Į
    -0.07
    atories
    -0.06
     Costs
    -0.06
    æĭ¿
    -0.06
    EAR
    -0.06
     Turns
    -0.06
     costs
    -0.06
    ozy
    -0.06
     notices
    -0.06
    POSITIVE LOGITS
    _generic
    0.07
     online
    0.07
    \Migration
    0.07
    isible
    0.07
    itung
    0.07
    enet
    0.06
    orgetown
    0.06
    online
    0.06
    'gc
    0.06
    -now
    0.06
    Activations Density 0.006%

    No Known Activations