INDEX

Explanations

phrases or statements emphasizing the main idea or point in a discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

loh

-0.15

eway

-0.15

ration

-0.15

TargetException

-0.15

opis

-0.14

ippers

-0.14

Ð¾Ð¿Ð¸Ñģ

-0.14

jay

-0.14

aggio

-0.14

amage

-0.13

POSITIVE LOGITS

 point

0.33

point

0.29

-point

0.27

 points

0.26

.point

0.25

points

0.24

 Point

0.24

 POINT

0.23

(point

0.23

(Point

0.22

Activations Density 0.030%

phrases or statements emphasizing the main idea or point in a discussion

No Comments

No Known Activations