© 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. 30033
    Prev
    Next
    INDEX
    Explanations

    aspects related to order processing and delivery logistics

    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
    _fu
    -0.07
    меÑī
    -0.07
    hammer
    -0.06
    adder
    -0.06
    .dw
    -0.06
    оÑĩÑĮ
    -0.06
    ç¼
    -0.06
    [js
    -0.06
     гла
    -0.06
    uan
    -0.06
    POSITIVE LOGITS
     delivery
    0.09
     arrival
    0.09
     shipped
    0.08
     arrive
    0.08
    arrival
    0.07
     arrived
    0.07
     deliver
    0.07
     Arrival
    0.07
     lleg
    0.07
     Delivery
    0.07
    Activations Density 0.008%

    No Known Activations