INDEX

Explanations

phrases related to uncertainty and complexity in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 convinced

-0.16

æĺİçĻ½

-0.15

utorial

-0.14

 think

-0.14

 klar

-0.14

.Navigator

-0.14

ial

-0.14

ores

-0.13

or

-0.13

explained

-0.13

POSITIVE LOGITS

 impossible

0.26

 imposs

0.24

 Impossible

0.24

 cannot

0.22

æĹłæ³ķ

0.22

Impossible

0.21

åıªèĥ½

0.21

cannot

0.20

 Ð½ÐµÐ²Ð¾Ð·Ð¼Ð¾Ð¶Ð½Ð¾

0.19

 inability

0.19

Activations Density 0.167%

phrases related to uncertainty and complexity in discussions

No Comments

No Known Activations