ortegaalfredo/ngram-knowledge-injector

ENGRAFT: write facts into an LLM's n-gram (Engram) memory table as a removable overlay: 100 facts in a 9 MB file, no weights touched, verified on llama.cpp GGUF (Qwen3.8-Flash-Next).

Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors

LLM system prompts & injections

Reasoning-effort editing for third-party models in DeepSeek Harness: per-model thinking levels with a knowledge base + protocol inference, edited inside the official Models page card.

Skills for the Gemma and model/agent interactions

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Awesome resources for in-context learning and prompt engineering: Mastery of the LLMs such as ChatGPT, GPT-3, and FlanT5, with up-to-date and cutting-edge updates.

Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results

🐼 Steer your LLMs and agents at the token level: A web tool for token visualization & control, model inspection, installation-free harness, and LLM & agent trajectory annotation.