INDEX

Explanations

variations of the word "shock" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

fty

-0.18

esa

-0.16

ania

-0.15

stvo

-0.15

ake

-0.15

hti

-0.14

Ð¸ÑģÐº

-0.14

ocide

-0.14

nty

-0.14

kses

-0.14

POSITIVE LOGITS

ingly

0.44

wave

0.30

waves

0.28

 absor

0.27

tober

0.23

 waves

0.22

Shock

0.20

 Shock

0.20

Wave

0.19

uede

0.19

Activations Density 0.014%

variations of the word "shock" and related terms

No Comments

No Known Activations