{"data":{"id":"4508a5b2-3ce7-4fbc-a2e8-48e3e4d08ab4","title":"From Stories to Features: Scaling Concept Vectors for AI Alignment & Interpretability","summary":"Researchers study feature vectors, directions in a language model's activation space that correspond to human-interpretable concepts such as honesty or deception. They build vectors from the difference in mean activations between synthetic concept and antagonist stories, scaling to 1,036 alignment-relevant concepts from 2M stories released publicly. The vectors generalize across six models from three families for detecting concepts and steering behavior, and are used to analyze jailbreak attacks and reasoning.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2610.24556v1","publishedAt":"2026-10-17T08:23:03.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-10-17T08:23:03.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":null,"llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}