INDEX

Explanations

code-related keywords and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 *****

-0.14

âĶģâĶģâĶģâĶģ

-0.14

tran

-0.13

enler

-0.13

 Folk

-0.13

 ðŁĺī↵↵

-0.13

 ðŁĻĤ↵↵

-0.13

aybe

-0.13

tml

-0.13

ederland

-0.12

POSITIVE LOGITS

etc

0.29

etc

0.22

atd

0.18

 ëĵ±ìĿĦ

0.17

 blah

0.16

ãģªãģ©

0.16

Ã¢

0.16

 ÑĤÐ¾ÑīÐ¾

0.15

 ëĵ±ìĿĺ

0.15

 ëĵ±

0.15

Activations Density 0.997%

code-related keywords and structures

No Comments

No Known Activations