The check
We tested unchanged Qwen3-8B and Qwen3-8B-Base checkpoints at seven boundaries after layers 4, 9, 14, 19, 23, 27, and 31.
Matched compression. PRF keeps exactly K features. Static SVD sends K BF16 coefficients in a prefit uncentered basis. K=205 out of 4,096 means 5.0049% of values are kept.
Where the hidden-state codec was inserted
The same seven intervention points were tested in separate PRF and static SVD arms.
What happened. Keeping 5.0049% of activation values at all seven boundaries strongly changed next-token behavior for this prompt. Static SVD caused less distortion than PRF at every matched rate, although neither remained close to dense behavior.
Less activation kept, more policy distortion
Delta NLL measures how much less likely each checkpoint makes its own dense continuation after compression. Zero is dense parity. Lower is better.
Qwen3-8B
Post-trained checkpoint
Qwen3-8B-Base
Pretraining-only checkpoint
Rank and spectrum status by layer
The SVD basis was fitted separately at each boundary. Stable and effective rank values in the source run span 1.0 to 2.6, while the component counts and held-out coverage below vary sharply by boundary.
Components needed for calibration energy
The vertical scale is logarithmic. The dashed line marks 5% kept (K=205), the operating point used in the layer-wise test.
Qwen3-8B
Post-trained checkpoint
Qwen3-8B-Base
Pretraining-only checkpoint
K@95 and K@99 are spectrum thresholds, not evaluated codec settings. The Base layer 31 K@99 threshold is 2,073, beyond the stored 2,048-component basis.
Energy captured at 5% kept (K=205)
Calibration energy is measured on the states used to fit each basis. Dense held-out energy tests the same basis on separate dense states. The vertical axis begins at 65% so the layer differences remain visible.
Qwen3-8B
Post-trained checkpoint
Qwen3-8B-Base
Pretraining-only checkpoint
Layer-wise behavior at 5% kept (K=205)
Each connected point applies compression at one boundary only, ordered by layer. Dashed lines show the result when the same codec is applied at all seven boundaries. Delta NLL uses a fixed token history, and lower is better.
Qwen3-8B
Post-trained checkpoint
Qwen3-8B-Base
Pretraining-only checkpoint
See the text itself. The metrics show the size of the shift. The companion report pairs dense references with recorded PRF and SVD generations at lighter and deeper compression.
View recorded outputs