INDEX

Explanations

instances of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

art

-0.15

be

-0.15

-INF

-0.15

 slightest

-0.15

il

-0.14

essel

-0.14

¼åĲĪ

-0.14

ï¿

-0.13

iam

-0.13

POSITIVE LOGITS

istrat

0.17

imli

0.15

©

0.15

éĻ½

0.15

strcasecmp

0.15

Ã¤ge

0.15

stral

0.15

 third

0.14

posix

0.14

.performance

0.14

Activations Density 0.156%

instances of the word "the."

No Comments

No Known Activations