© 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. 94175
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and their player acquisitions

    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
    omit
    -0.08
    ihan
    -0.07
    nock
    -0.07
    celik
    -0.07
    ampie
    -0.07
    bai
    -0.07
     povÄĽ
    -0.07
    amma
    -0.07
    ogi
    -0.07
    оÑĢаÑı
    -0.07
    POSITIVE LOGITS
     hired
    0.10
     acquisitions
    0.10
     purchased
    0.09
     purchase
    0.09
     foreign
    0.08
     bought
    0.08
     hire
    0.08
     acquisition
    0.08
    urchased
    0.08
     imported
    0.08
    Activations Density 0.061%

    No Known Activations