© 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. 86395
    Prev
    Next
    INDEX
    Explanations

    references to international investment trends and foreign buyers in real estate

    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
     Lange
    -0.06
     Roosevelt
    -0.06
    xico
    -0.06
    estroy
    -0.06
     analogue
    -0.06
     bump
    -0.06
    phans
    -0.06
    ader
    -0.06
     incumb
    -0.05
     scand
    -0.05
    POSITIVE LOGITS
     purchases
    0.09
     buying
    0.09
     buys
    0.09
    -buy
    0.09
    foreign
    0.09
     purchase
    0.09
    кÑĥп
    0.08
     foreigners
    0.08
     foreign
    0.08
    æµ·å¤ĸ
    0.08
    Activations Density 0.009%

    No Known Activations