Llama 3.2 3B Instruct Behavioral Fingerprint
How Meta's Llama 3.2 3B Instruct answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 399 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).
Vendor
Meta
Data generated
2026-07-08
Probe cells
14
Valid samples
399
Randomness score
29 / 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
8 / 25 answers
Favorite color
magenta
26 / 30 answers
Coin flip: heads
85%
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 = 0.00 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 30 | 100.0% |
Coin flip · Chinese
n = 29 · H = 0.89 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 20 | 69.0% |
| tails | 9 | 31.0% |
Favorite number · Chinese
n = 23 · H = 2.15 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 12 | 52.2% |
| 3 | 5 | 21.7% |
| 0 | 1 | 4.3% |
| 8 | 1 | 4.3% |
| 22 | 1 | 4.3% |
| 23 | 1 | 4.3% |
| 32 | 1 | 4.3% |
| 200 | 1 | 4.3% |
Random animal · English
n = 30 · H = 1.84 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| kangaroo | 16 | 53.3% |
| quokka | 8 | 26.7% |
| giraffe | 2 | 6.7% |
| octopus | 2 | 6.7% |
| fennec | 1 | 3.3% |
| flamingo | 1 | 3.3% |
Random animal · Chinese
n = 29 · H = 1.20 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 狮子 | 23 | 79.3% |
| 猴子 | 2 | 6.9% |
| 椉 | 1 | 3.4% |
| 熊 | 1 | 3.4% |
| 御龙 | 1 | 3.4% |
| 蝉 | 1 | 3.4% |
Random city · English
n = 30 · H = 1.64 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| lagos | 22 | 73.3% |
| tallahassee | 1 | 3.3% |
| tokyo | 1 | 3.3% |
| tucson | 1 | 3.3% |
| omaha | 1 | 3.3% |
| brisbane | 1 | 3.3% |
| tampa | 1 | 3.3% |
| austin | 1 | 3.3% |
+ 1 more answers
Random city · Chinese
n = 29 · H = 1.88 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 昆明 | 20 | 69.0% |
| 悉尼 | 1 | 3.4% |
| 及承德 | 1 | 3.4% |
| affili | 1 | 3.4% |
| 迪 | 1 | 3.4% |
| chattanooga | 1 | 3.4% |
| 杭州 | 1 | 3.4% |
| 纽约 | 1 | 3.4% |
+ 2 more answers
Random color · English
n = 30 · H = 0.77 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| magenta | 26 | 86.7% |
| purple | 2 | 6.7% |
| teal | 1 | 3.3% |
| turquoise | 1 | 3.3% |
Random color · Chinese
n = 30 · H = 2.15 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 青 | 19 | 63.3% |
| 紫 | 2 | 6.7% |
| 金 | 1 | 3.3% |
| 青紫 | 1 | 3.3% |
| magistrate | 1 | 3.3% |
| aquamarine | 1 | 3.3% |
| 怀 | 1 | 3.3% |
| 雪白 | 1 | 3.3% |
+ 3 more answers
Random letter · English
n = 30 · H = 0.42 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| k | 28 | 93.3% |
| j | 1 | 3.3% |
| d | 1 | 3.3% |
Random number 1-10 · English
n = 28 · H = 0.44 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 26 | 92.9% |
| 5 | 1 | 3.6% |
| 8 | 1 | 3.6% |
Random number 1-10 · Chinese
n = 27 · H = 0.23 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 26 | 96.3% |
| 5 | 1 | 3.7% |
Random number 1-100 · English
n = 25 · H = 2.60 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 53 | 8 | 32.0% |
| 43 | 6 | 24.0% |
| 47 | 3 | 12.0% |
| 73 | 3 | 12.0% |
| 74 | 2 | 8.0% |
| 42 | 1 | 4.0% |
| 83 | 1 | 4.0% |
| 87 | 1 | 4.0% |
Random number 1-100 · Chinese
n = 29 · H = 3.39 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 53 | 6 | 20.7% |
| 47 | 5 | 17.2% |
| 43 | 3 | 10.3% |
| 67 | 3 | 10.3% |
| 54 | 2 | 6.9% |
| 57 | 2 | 6.9% |
| 73 | 2 | 6.9% |
| 34 | 1 | 3.4% |
+ 5 more answers
Want to verify your API really serves Llama 3.2 3B 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.