© 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. 5-LLAMASCOPE-RES-131K
    11. 126534
    Prev
    Next
    INDEX
    Explanations

    terms related to steam and water systems in industrial contexts

    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
    ewe
    -0.06
    aal
    -0.06
     examiner
    -0.06
     han
    -0.06
     al
    -0.06
    _lang
    -0.06
     ì±Ħ
    -0.06
    uggage
    -0.06
    >null
    -0.05
    icy
    -0.05
    POSITIVE LOGITS
    Ĩ
    0.07
    elas
    0.07
    olon
    0.06
    qing
    0.06
    adlo
    0.06
     Miguel
    0.06
    esch
    0.06
    íķĻíļĮ
    0.06
    eton
    0.06
    /pdf
    0.06
    Activations Density 0.001%

    No Known Activations