© 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. 15-LLAMASCOPE-RES-131K
    11. 89830
    Prev
    Next
    INDEX
    Explanations

    elements related to shopping cart functionality

    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
    oud
    -0.07
    lett
    -0.06
    dit
    -0.06
    istar
    -0.06
    jan
    -0.06
     ld
    -0.06
    amide
    -0.06
     Kı
    -0.06
    ear
    -0.06
    leans
    -0.06
    POSITIVE LOGITS
    Unnamed
    0.07
    PCI
    0.07
     ENTER
    0.07
    ormsg
    0.07
    Montserrat
    0.07
    оÑĢаз
    0.06
     taxable
    0.06
    .EntityManager
    0.06
    anax
    0.06
     Españ
    0.06
    Activations Density 0.007%

    No Known Activations