INDEX

Explanations

variations of the word "use" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

layers

-0.16

Ã©t

-0.15

oux

-0.15

ayer

-0.15

acie

-0.14

xin

-0.14

 Kinder

-0.14

-0.13

adera

-0.13

ayers

-0.13

POSITIVE LOGITS

hic

0.15

 Shoulder

0.14

erde

0.14

FE

0.14

mouseup

0.13

frames

0.13

mir

0.13

Ð¼Ð°ÑĤ

0.13

.Formatting

0.13

ĻĤ

0.13

Activations Density 0.046%

variations of the word "use" in different contexts

No Comments

No Known Activations