© 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. 60969
    Prev
    Next
    INDEX
    Explanations

    phrases related to purchasing decisions and considerations

    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
    ube
    -0.07
    anta
    -0.07
    eldon
    -0.07
    ervo
    -0.06
    antan
    -0.06
    clud
    -0.06
    tel
    -0.06
    igin
    -0.06
    lique
    -0.06
    Ìī
    -0.06
    POSITIVE LOGITS
     purchase
    0.12
     purchases
    0.10
     purchased
    0.10
     replacement
    0.10
    purchase
    0.09
     Purchase
    0.09
    -buy
    0.08
    è´Ńä¹°
    0.08
     replacements
    0.08
    Purchase
    0.08
    Activations Density 0.013%

    No Known Activations