© 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. 57511
    Prev
    Next
    INDEX
    Explanations

    terms related to business acquisitions and mergers

    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
    -0.06
    инок
    -0.06
    Ú¯ÛĮ
    -0.06
    calar
    -0.06
     Mint
    -0.06
    ustr
    -0.06
     eid
    -0.06
    wart
    -0.06
     hear
    -0.05
    /bit
    -0.05
    POSITIVE LOGITS
    isto
    0.08
    ee
    0.08
    à¤Łà¤ķ
    0.07
    .infinity
    0.07
     spree
    0.07
    CompleteListener
    0.07
    imir
    0.07
    λή
    0.06
    /helper
    0.06
    pedia
    0.06
    Activations Density 0.012%

    No Known Activations