SAE 特徵提取：從殘差流看見模型內部表示
Anthropic 的研究團隊在 Claude 3 Sonnet 中訓練了高達 3400 萬個特徵的稀疏編碼器（SAE），提取出可解釋的特徵表示。研究顯示能對模型輸出行為產生因果影響，為 AI 安全治理提供了可研究的內部訊號與潛在工具，但忠實度仍需驗證。
Technical
IT industry technical articles covering AWS, Azure, Java, Python, SQL, DevOps, and more.
SAE Feature Extraction: Seeing Model Representations Through the Residual Stream
Anthropic’s research team trained sparse autoencoders (SAEs) with up to 34 million features in Claude 3 Sonnet, extracting interpretable feature representations. The research shows causal effects on model output behavior, providing internal signals and potential tools that can be studied for AI safety governance, though faithfulness still requires validation.
GDM AI Control Roadmap：為假設性的 AI 威脅建立防禦藍圖
當 AI Agent 逐漸具備自主能力，我們該如何防範尚未發生的風險？DeepMind 最新研究提出 TRAIT&R 分類法，搭配 D1–D4 偵測與 R1–R3 回應的分層防禦機制，為企業提供一套在威脅真正成形之前就能先行部署、並逐層驗證成效的安全藍圖。
GDM AI Control Roadmap: A Defensive Blueprint for Hypothetical AI Threats
As AI agents gain autonomy, how do you defend against risks that have not happened yet? DeepMind’s TRAIT&R taxonomy maps D1–D4 detection onto R1–R3 response.
Beyond Chinchilla: How Do You Balance Training and Inference Costs?
When inference demand is extremely high, following the Chinchilla rule can actually be more expensive. This article explains how a “small model, more data” strategy can find a new balance point in the total cost of training and inference.
Constitutional AI: 如何透過 AI Feedback 實現自動化安全治理
標註員 A 給 5 分，B 給 1 分。同一個回答。傳統 RLHF 的瓶頸不在成本，而在訊號雜訊比。本文解析 Constitutional AI 如何透過 AI Feedback 建立自動化安全邊界，以及落地時需要評估的成本結構。
Constitutional AI: How AI Feedback Enables Automated Safety Governance
Annotator A gives it a 5, annotator B gives it a 1. The same answer. The bottleneck in traditional RLHF is not cost, but the signal-to-noise ratio. This article breaks down how Constitutional AI uses AI Feedback to build automated safety boundaries, and the cost structure teams need to evaluate when putting it into practice.
Toy Models of Superposition：神經網路的特徵壓縮術
打開 IDE。你觀察隱藏層的單一神經元。它同時響應了 ‘Python’ 和 ‘錯誤處理’。這不是 bug，這是特徵壓縮。Anthropic 的 Toy Models 研究揭示特徵稀疏性如何驅動「疊加（Superposition）」現象，解釋模型如何在容量限制下儲存更多概念。
Toy Models of Superposition: Feature Compression in Neural Networks
Open your IDE. You observe a single hidden-layer neuron. It responds to both “Python” and “error handling.” This is not a bug; it is feature-level compression. Anthropic’s Toy Models research reveals how feature sparsity drives “superposition,” explaining how models store more concepts under capacity constraints.
Chinchilla Scaling Laws: 算力預算下的模型與資料比例優化
算力預算有限時，該追求大模型還是大資料？透過 Chinchilla 論文數據，解析 1:20 參數與 Token 的最優比例，為 LLM 訓練提供決策依據。