© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3134
    Prev
    Next
    INDEX
    Explanations

    references to pricing and discounts in travel-related 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
    uraa
    -0.07
    iro
    -0.07
    erus
    -0.06
    /comments
    -0.06
    xae
    -0.06
     rud
    -0.06
     Natural
    -0.05
    onomies
    -0.05
    illion
    -0.05
     screening
    -0.05
    POSITIVE LOGITS
     offers
    0.08
    ylan
    0.07
     offer
    0.07
     رÙħضاÙĨ
    0.07
     codes
    0.07
    estr
    0.07
    лаг
    0.07
    FLASH
    0.07
     occas
    0.07
     Offers
    0.07
    Activations Density 0.016%

    No Known Activations