INDEX

Explanations

the word "every" to emphasize universality or generality in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ovky

-0.15

 possibly

-0.15

rompt

-0.14

zos

-0.14

orum

-0.14

 dÃłi

-0.14

 possible

-0.14

Ð»ÑİÑĩ

-0.14

ees

-0.14

ourke

-0.13

POSITIVE LOGITS

time

0.23

 year

0.21

 once

0.21

 time

0.20

 effort

0.19

 successful

0.17

 attempt

0.17

Å¾i

0.16

body

0.16

 person

0.16

Activations Density 0.051%

the word "every" to emphasize universality or generality in statements

No Comments

No Known Activations