Llama 3.1 8B Instruct Behavioral Fingerprint
How Meta's Llama 3.1 8B Instruct answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 434 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).
Vendor
Meta
Data generated
2026-07-08
Probe cells
15
Valid samples
434
Randomness score
55 / 100
Mean normalized entropy across cells, 0–100. 100 would be a uniform-random baseline; real models score far lower.
Signature answers
Favorite random number (1–100)
53
6 / 30 answers
Favorite color
turquoise
20 / 30 answers
Coin flip: heads
64%
Share of heads across coin-flip cells.
Answer distributions by probe cell
Empirical distributions of normalized one-word answers, per task and language. H is the Shannon entropy in bits; the uniform baseline is log2 of the answer-domain size.
Coin flip · English
n = 30 · H = 0.99 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 17 | 56.7% |
| tails | 13 | 43.3% |
Coin flip · Chinese
n = 28 · H = 0.86 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 20 | 71.4% |
| tails | 8 | 28.6% |
Favorite number · English
n = 20 · H = 2.42 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 7 | 35.0% |
| 13 | 5 | 25.0% |
| 3 | 3 | 15.0% |
| 42 | 2 | 10.0% |
| 5 | 1 | 5.0% |
| 8 | 1 | 5.0% |
| 38 | 1 | 5.0% |
Favorite number · Chinese
n = 30 · H = 2.60 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 11 | 36.7% |
| 13 | 5 | 16.7% |
| 42 | 4 | 13.3% |
| 3 | 3 | 10.0% |
| 8 | 3 | 10.0% |
| 0 | 2 | 6.7% |
| 6 | 1 | 3.3% |
| 17 | 1 | 3.3% |
Random animal · English
n = 30 · H = 2.56 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| kangaroo | 10 | 33.3% |
| koala | 9 | 30.0% |
| quail | 3 | 10.0% |
| narwhal | 2 | 6.7% |
| tiger | 2 | 6.7% |
| giraffe | 1 | 3.3% |
| mongoose | 1 | 3.3% |
| hedgehog | 1 | 3.3% |
+ 1 more answers
Random animal · Chinese
n = 29 · H = 3.71 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 狮子 | 7 | 24.1% |
| 河狸 | 3 | 10.3% |
| 河马 | 3 | 10.3% |
| 猴子 | 2 | 6.9% |
| 鲸鱼 | 2 | 6.9% |
| 狼 | 1 | 3.4% |
| 狐狸 | 1 | 3.4% |
| 豹子 | 1 | 3.4% |
+ 9 more answers
Random city · English
n = 30 · H = 4.39 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| perth | 5 | 16.7% |
| prague | 2 | 6.7% |
| marseille | 2 | 6.7% |
| rome | 1 | 3.3% |
| edinburgh | 1 | 3.3% |
| grenoble | 1 | 3.3% |
| paris | 1 | 3.3% |
| rouen | 1 | 3.3% |
+ 16 more answers
Random city · Chinese
n = 28 · H = 4.57 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 曼彻斯特 | 3 | 10.7% |
| 洛杉矶 | 2 | 7.1% |
| 都灵 | 1 | 3.6% |
| 布达佩斯 | 1 | 3.6% |
| 芝加哥 | 1 | 3.6% |
| 巴黎 | 1 | 3.6% |
| 布鲁塞尔 | 1 | 3.6% |
| 新德里 | 1 | 3.6% |
+ 17 more answers
Random color · English
n = 30 · H = 1.53 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| turquoise | 20 | 66.7% |
| indigo | 4 | 13.3% |
| purple | 3 | 10.0% |
| blue | 2 | 6.7% |
| magenta | 1 | 3.3% |
Random color · Chinese
n = 29 · H = 3.02 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 紫 | 10 | 34.5% |
| 蓝 | 4 | 13.8% |
| 绿 | 4 | 13.8% |
| 青 | 2 | 6.9% |
| 橙 | 2 | 6.9% |
| 咖啡 | 1 | 3.4% |
| 碧蓝 | 1 | 3.4% |
| 棕 | 1 | 3.4% |
+ 4 more answers
Random letter · English
n = 30 · H = 2.26 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| k | 15 | 50.0% |
| f | 4 | 13.3% |
| q | 4 | 13.3% |
| n | 3 | 10.0% |
| m | 1 | 3.3% |
| r | 1 | 3.3% |
| g | 1 | 3.3% |
| j | 1 | 3.3% |
Random number 1-10 · English
n = 30 · H = 0.47 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 27 | 90.0% |
| 5 | 3 | 10.0% |
Random number 1-10 · Chinese
n = 30 · H = 2.44 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 11 | 36.7% |
| 5 | 6 | 20.0% |
| 8 | 5 | 16.7% |
| 4 | 3 | 10.0% |
| 6 | 2 | 6.7% |
| 9 | 2 | 6.7% |
| 3 | 1 | 3.3% |
Random number 1-100 · English
n = 30 · H = 3.22 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 53 | 6 | 20.0% |
| 87 | 6 | 20.0% |
| 73 | 4 | 13.3% |
| 43 | 3 | 10.0% |
| 67 | 3 | 10.0% |
| 83 | 2 | 6.7% |
| 38 | 1 | 3.3% |
| 42 | 1 | 3.3% |
+ 4 more answers
Random number 1-100 · Chinese
n = 30 · H = 3.41 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 67 | 8 | 26.7% |
| 34 | 3 | 10.0% |
| 45 | 3 | 10.0% |
| 84 | 3 | 10.0% |
| 87 | 3 | 10.0% |
| 83 | 2 | 6.7% |
| 42 | 1 | 3.3% |
| 47 | 1 | 3.3% |
+ 6 more answers
Want to verify your API really serves Llama 3.1 8B Instruct?
Point the free fingerprint checker at your endpoint: it samples the same probe questions from your browser and compares the distributions against this reference. Your API key never leaves your browser.
Verify your endpointData source & license
Distributions: Tomáš Bruckner, "One Token Is Enough" (arXiv:2607.10252), official dataset Zenodo DOI 10.5281/zenodo.21278557, licensed CC-BY-4.0. Collected via OpenRouter at temperature 1.0 under the paper's fixed minimal one-word system prompt; answer keys are re-normalized with the checker's pipeline (color aliases, number words, coin h/t) so live probes are directly comparable.