INDEX

Explanations

mentions of nationalities or ethnic groups, particularly focusing on Chinese and Japanese references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

umer

-0.15

anan

-0.14

ular

-0.14

 United

-0.14

ĥĿ

-0.14

gings

-0.14

ULAR

-0.14

ffffffff

-0.13

POSITIVE LOGITS

-American

0.36

-Russian

0.32

-speaking

0.28

-Americans

0.27

-language

0.24

ischer

0.23

-born

0.22

-Israel

0.21

-European

0.20

istan

0.20

Activations Density 0.205%

mentions of nationalities or ethnic groups, particularly focusing on Chinese and Japanese references

No Comments

No Known Activations