© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118594
    Prev
    Next
    INDEX
    Explanations

    terms related to currency value and trade dynamics

    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
    orca
    -0.07
    odiac
    -0.07
     cul
    -0.07
     systems
    -0.06
    angan
    -0.06
     tubes
    -0.06
     foundation
    -0.06
     corner
    -0.06
     Associ
    -0.06
    .cf
    -0.06
    POSITIVE LOGITS
    foreign
    0.08
     foreign
    0.07
    огÑĢа
    0.07
     competitiveness
    0.07
    окÑĥ
    0.07
    uffer
    0.07
     exporting
    0.07
    compet
    0.07
    translation
    0.07
    Foreign
    0.07
    Activations Density 0.014%

    No Known Activations