© 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. 126791
    Prev
    Next
    INDEX
    Explanations

    references to food and beverage ingredient standards and safety

    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
    ñana
    -0.08
     ÄĮer
    -0.07
    ghan
    -0.07
    atars
    -0.07
    inke
    -0.07
    otionEvent
    -0.07
    _Config
    -0.07
     FactoryBot
    -0.07
    682
    -0.07
     Martins
    -0.07
    POSITIVE LOGITS
     pres
    0.07
     nor
    0.07
     ingredients
    0.07
    indi
    0.07
     artificial
    0.07
     contain
    0.07
     trace
    0.07
     contains
    0.07
    iesen
    0.06
     ingredient
    0.06
    Activations Density 0.005%

    No Known Activations