© 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. 16556
    Prev
    Next
    INDEX
    Explanations

    mentions of market analysis and statistical data

    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
    lectron
    -0.07
    mps
    -0.07
    horn
    -0.07
    ķĮ
    -0.06
    arte
    -0.06
    assage
    -0.06
    ạt
    -0.06
    apur
    -0.06
    FontAwesome
    -0.06
    ehr
    -0.06
    POSITIVE LOGITS
     shipments
    0.07
     sales
    0.07
     models
    0.07
     market
    0.07
    öm
    0.06
     vendors
    0.06
     growth
    0.06
     shipment
    0.06
    une
    0.06
     Models
    0.06
    Activations Density 0.003%

    No Known Activations