© 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. 79273
    Prev
    Next
    INDEX
    Explanations

    phrases related to purchasing and acquiring goods or products

    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
     Fortune
    -0.06
     property
    -0.06
    ossip
    -0.05
    passport
    -0.05
    irsch
    -0.05
     Passport
    -0.05
     Daily
    -0.05
    ilt
    -0.05
     Lunch
    -0.05
     Property
    -0.05
    POSITIVE LOGITS
     Amazon
    0.10
    Amazon
    0.10
    -order
    0.09
     order
    0.09
     amazon
    0.09
     orders
    0.09
    amazon
    0.09
     ORDER
    0.09
    asan
    0.08
    ibar
    0.08
    Activations Density 0.020%

    No Known Activations