© 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. 17-LLAMASCOPE-RES-131K
    11. 74586
    Prev
    Next
    INDEX
    Explanations

    phrases related to delivery services and food options

    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
    positor
    -0.06
    ResponseStatus
    -0.06
    inki
    -0.06
    одо
    -0.06
    ná
    -0.06
    LT
    -0.06
    lepÅ¡ÃŃ
    -0.05
     duties
    -0.05
    _HI
    -0.05
    ãĥ¼ãĥª
    -0.05
    POSITIVE LOGITS
     delivery
    0.15
     Delivery
    0.14
    delivery
    0.13
    Delivery
    0.12
     deliveries
    0.12
    -del
    0.12
     delivered
    0.11
    _delivery
    0.11
    -order
    0.10
     Deliver
    0.10
    Activations Density 0.098%

    No Known Activations