Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4930
    Prev
    Next
    INDEX
    Explanations

    cooking instructions and food preparation steps

    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
    iosis
    -0.07
    æĿ¡
    -0.07
    acz
    -0.06
    ä¸ĭåİ»
    -0.06
    Formats
    -0.06
    kee
    -0.06
    à¹Īาà¸ģ
    -0.06
     ntohs
    -0.06
    stdClass
    -0.06
    73
    -0.06
    POSITIVE LOGITS
     overnight
    0.17
     Overnight
    0.15
     refriger
    0.12
    overn
    0.11
     Refriger
    0.10
     refrigerator
    0.10
     fridge
    0.09
     Hour
    0.09
     freezer
    0.08
     chilling
    0.08
    Activations Density 0.030%

    No Known Activations