INDEX

Explanations

visual elements and contextual details related to health, community, and military scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

bbe

-0.16

opup

-0.16

oeff

-0.15

adera

-0.15

gressor

-0.15

ÐºÐ¾Ð²Ñĸ

-0.14

plor

-0.14

/Dk

-0.14

igar

-0.14

.scalablytyped

-0.14

POSITIVE LOGITS

 REUTERS

0.19

ected

0.18

 during

0.17

 seen

0.17

ÙĤ

0.16

 react

0.16

 FILE

0.16

 displayed

0.16

during

0.16

 perceived

0.15

Activations Density 0.060%

visual elements and contextual details related to health, community, and military scenarios

No Comments

No Known Activations