© 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 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. 55988
    Prev
    Next
    INDEX
    Explanations

    mentions of prices and their increases across various 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
    o
    -0.06
     bonus
    -0.06
     (
    -0.05
     grade
    -0.05
     cav
    -0.05
    ëĤ
    -0.05
    (
    -0.05
     slightly
    -0.05
     impressions
    -0.05
    y
    -0.05
    POSITIVE LOGITS
    prices
    0.11
    flation
    0.10
     prices
    0.10
     inflation
    0.10
    Prices
    0.10
    uitka
    0.09
     Consumer
    0.09
     Prices
    0.09
    OptionsResolver
    0.09
    涨
    0.08
    Activations Density 0.035%

    No Known Activations