© 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. 16312
    Prev
    Next
    INDEX
    Explanations

    references to data warehousing concepts and techniques

    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
    #
    -0.07
     contag
    -0.07
    setParameter
    -0.07
    htub
    -0.06
    engo
    -0.06
     иÑģпÑĭÑĤ
    -0.06
     jspb
    -0.06
    emo
    -0.06
     crowdfunding
    -0.06
     recruiting
    -0.06
    POSITIVE LOGITS
    arehouse
    0.08
    ickey
    0.07
     warehouse
    0.07
    _lazy
    0.07
    ãĥ¼ãĥ³
    0.07
     Alta
    0.06
    浪
    0.06
    iew
    0.06
    abase
    0.06
     Pent
    0.06
    Activations Density 0.004%

    No Known Activations