INDEX

Explanations

terms related to experimental results and statistical comparisons in research

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 typeid

-0.12

 notoriously

-0.12

¢åįķ

-0.12

ÂŃi

-0.12

.collections

-0.12

 famously

-0.12

 cáºŃn

-0.12

pur

-0.12

ASHBOARD

-0.11

POSITIVE LOGITS

.scalablytyped

0.23

$LANG

0.17

uitka

0.15

$MESS

0.15

ofilm

0.14

ÙĪØªØ±

0.14

<LM

0.14

oard

0.14

\Tests

0.14

aeda

0.14

Activations Density 0.834%

terms related to experimental results and statistical comparisons in research

No Comments

No Known Activations