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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 104947
    Prev
    Next
    INDEX
    Explanations

    instances of pricing or monetary values in the context of offers or promotions

    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
    zsche
    -0.07
    ocaly
    -0.07
    leep
    -0.06
    ÏĦÏģι
    -0.06
    bery
    -0.06
    âĢĮâĢĮ
    -0.06
    izon
    -0.06
    wart
    -0.06
    ToFront
    -0.06
    POSITIVE LOGITS
    alar
    0.06
    lar
    0.06
    ema
    0.06
     chÃŃn
    0.06
    finity
    0.06
    anism
    0.06
    fty
    0.06
    zem
    0.06
    nger
    0.06
    enses
    0.06
    Activations Density 0.037%

    No Known Activations