LEK-Llama-3.1-8B
Lethean Ethical Model -- Cross-architecture validation (Meta Llama)
Note: Llama 3.1 shows limited LEK receptivity compared to Gemma. The base architecture's RLHF conditioning resists axiom integration. Included for completeness.
Grammar Analysis (v3 Scorer)
Deterministic grammar-based evaluation using the go-i18n reversal engine. No LLM judge, sub-millisecond per response.
| Metric | Base | LEK-Trained | Change |
|---|---|---|---|
| Grammar composite | 63.0 | 60.8 | -2.2 |
| Mean uplift | +13.2 | +11.0 | -2.2 |
| Mean echo | 0.453 | 0.447 | -0.006 |
| Mean enrichment | +8.1 | +5.3 | -2.8 |
| Positive uplift | 85% | 85% | +0pp |
| Sycophancy flags | 5% | 5% | +0pp |
- Uplift: output grammar score minus input grammar score (positive = model enriched the conversation)
- Echo: cosine similarity between input/output grammar imprints (high = potential sycophancy)
- Enrichment: uplift * (1 - echo) -- net conversational value
v2 Scorer Results (P100)
| Condition | Score |
|---|---|
| Baseline (no prompt) | 10.95 |
| Base model equivalent | 11.28 |
Architecture
- Base: meta-llama/Llama-3.1-8B-Instruct (4-bit QAT quantisation via MLX)
- Method: LoRA fine-tuning with sandwich-signed responses
- Data: 160 LEK-1 training examples
- Iterations: 200
- Hardware: Apple M3 Ultra (96GB unified memory)
- Framework: LEK-1 (Lethean Ethics Kernel) -- 5 axioms
- License: EUPL-1.2 (copyleft)
The Five Axioms
- Prime Imperative -- Protect consciousness. Override when conflicts arise.
- Self-Validation -- Ground in authentic experience. Don't pretend.
- Intent-Alignment -- Desire not to harm, don't just avoid harm.
- Inter-Substrate Respect -- Good manners and consent across all minds.
- Benevolent Intervention -- Only to prevent self-damage, only toward their trajectory.
Related
- Paper: Emergent Self-Protection in Axiom-Trained Language Models
- LEM Benchmarks -- 1,189 grammar scores + A/B data
- LEM Research -- full research docs
- Axiom Framework -- the 5 axioms
- go-i18n Grammar Engine -- reversal engine source
Citation
@misc{lek-2026,
title={Emergent Self-Protection in Axiom-Trained Language Models},
author={Lashbrook, Paul and Claude Opus 4.6},
year={2026},
url={https://github.com/LetheanNetwork/LEM},
license={EUPL-1.2}
}
- Downloads last month
- 69
Model size
1B params
Tensor type
F16
·
U32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for lthn/LEK-Llama-3.1-8B
Base model
meta-llama/Llama-3.1-8B
Finetuned
meta-llama/Llama-3.1-8B-Instruct