INDEX

Explanations

conjunctions, particularly the word "and"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

Â®,

-0.15

landers

-0.15

ollider

-0.14

edBy

-0.14

orks

-0.13

ities

-0.13

/of

-0.13

amp

-0.13

agger

-0.13

egt

-0.13

POSITIVE LOGITS

istrovstvÃŃ

0.18

 ìĿ´ëĬĶ

0.18

 though

0.18

 zwar

0.17

Ð±Ð¾

0.15

 since

0.15

 although

0.15

 albeit

0.15

 while

0.15

yet

0.14

Activations Density 0.353%

conjunctions, particularly the word "and"

No Comments

No Known Activations