Lohe Ar Decoder
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
Lohe Ar Decoder has 14 facts recorded in Dontopedia across 2 references, with 1 live disagreement.
Mostly:has parameter(3), commits to spherical geometry(1), deployed in(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (4)
Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.
announcesPushAnnounces Push(1)
- Message 2026 03 14 06 44
ex:message-2026-03-14-06-44
isIs(1)
- Pipeline Stage 5
ex:pipeline-stage-5
outputsToOutputs to(1)
- Code Lm
ex:code-lm
precedesStagePrecedes Stage(1)
- Code Lm
ex:code-lm
Other facts (14)
The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.
| Predicate | Value | Ref |
|---|---|---|
| Has Parameter | d=384 | [2] |
| Has Parameter | 3-layers | [2] |
| Has Parameter | 15k-steps | [2] |
| Commits to Spherical Geometry | S D 1 | [1] |
| Deployed in | Rjs Lohedec | [1] |
| Has Dimension | 384 | [1] |
| Has Num Layers | 3 | [1] |
| Precedes Stage | Bytes | [1] |
| Produces | Vmf Byte Logits | [1] |
| Running in Branch | Rjs Lohedec | [1] |
| Trained for Steps | 15000 | [1] |
| Has Status | running | [2] |
| Has Output Type | Vmf Byte Logits | [2] |
| Outputs to | bytes | [2] |
Timeline
Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.
References (2)
ctx:discord/blah/watt-activation/part-302ctx:discord/blah/watt-activation/300- full textwatt-activation-300text/plain3 KB
doc:agent/watt-activation-300/3b6edccf-3524-4608-838f-25890efaea15Show excerpt
[2026-03-14 06:34] xenonfun: ``` 3. Manual attention (lines 110-128) — Hand-rolled softmax attention instead of using mx.fast.scaled_dot_product_attention. MLX's fused attention kernel is significantly faster for small sequence lengths. …
See also
Keep researching
Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.