© 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. 28799
    Prev
    Next
    INDEX
    Explanations

    phrases related to commerce and trade practices

    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
    .scalablytyped
    -0.08
    λιά
    -0.06
    è²»
    -0.06
     scept
    -0.06
    ovit
    -0.06
    ÑĤеÑĢи
    -0.06
    wahl
    -0.06
     subur
    -0.06
    Bits
    -0.06
    kehr
    -0.06
    POSITIVE LOGITS
     export
    0.09
    -import
    0.08
    export
    0.08
    -export
    0.08
     cargo
    0.07
     Export
    0.07
     import
    0.07
    .export
    0.07
     trade
    0.07
    irq
    0.07
    Activations Density 0.008%

    No Known Activations