INDEX

Explanations

instances of the word "initial" and its variations

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

Negative Logits

ess

-0.18

ese

-0.17

eking

-0.16

Ð½Ð¾ÑģÑı

-0.16

ep

-0.15

æł·çļĦ

-0.14

ArgumentException

-0.14

ulk

-0.14

ats

-0.14

.her

-0.14

POSITIVE LOGITS

mente

0.24

/original

0.22

aneously

0.20

iative

0.20

lest

0.18

izers

0.17

most

0.17

isation

0.17

ised

0.17

 responders

0.17

Activations Density 0.015%

instances of the word "initial" and its variations

No Known Activations