INDEX

Explanations

references to historical events and the movements of groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

iliz

-0.19

 Ð¶Ð¸Ð»

-0.17

tring

-0.16

 ÎµÎ¯ÏĩÎµ

-0.16

sah

-0.16

aliz

-0.16

 camb

-0.15

å¯

-0.15

Å¾il

-0.15

 trov

-0.15

POSITIVE LOGITS

 were

0.43

Were

0.42

 Were

0.42

were

0.38

 weren

0.34

 waren

0.33

 fueron

0.32

 Ð±ÑĭÐ»Ð¸

0.29

 Ø¨ÙĪØ¯ÙĨØ¯

0.29

 byli

0.28

Activations Density 0.033%

references to historical events and the movements of groups

No Comments

No Known Activations