© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3329
    Prev
    Next
    INDEX
    Explanations

    phrases related to ordering or placing requests

    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
     Bott
    -0.07
    porter
    -0.06
    brew
    -0.06
    554
    -0.06
    SPA
    -0.06
    lander
    -0.06
    fit
    -0.06
     Selling
    -0.06
    spiel
    -0.06
     upon
    -0.06
    POSITIVE LOGITS
     orders
    0.10
    orders
    0.09
    -orders
    0.08
    order
    0.08
     order
    0.08
     заказ
    0.08
    订åįķ
    0.07
    'order
    0.07
    -order
    0.07
     Orders
    0.07
    Activations Density 0.005%

    No Known Activations