© 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. 75132
    Prev
    Next
    INDEX
    Explanations

    references to business and economic collaboration or initiatives

    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
    ponsive
    -0.07
     æ´
    -0.07
    ukkan
    -0.06
    ãĤ¦ãĤ¹
    -0.06
    /Internal
    -0.06
    æk
    -0.06
    ↵↵
    -0.06
    :UITableView
    -0.06
    IBM
    -0.06
     зб
    -0.06
    POSITIVE LOGITS
     gin
    0.08
    iggins
    0.07
     Stranger
    0.07
    utch
    0.06
     Tencent
    0.06
    ersh
    0.06
    лин
    0.06
    itten
    0.06
     Westbrook
    0.06
    adia
    0.06
    Activations Density 0.002%

    No Known Activations