INDEX

Explanations

phrases indicating tasks or processes that are described as easy or simple

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

Ð²Ð¸ÑĩÐ°Ð¹

-0.15

 æ®

-0.15

Rig

-0.15

ISIBLE

-0.14

ourcem

-0.14

ismet

-0.14

oodle

-0.14

POSITIVE LOGITS

nor

0.24

Nor

0.17

 anymore

0.17

 Ø¨ÙĦÚ©Ùĩ

0.17

Ð¾Ð³Ñĥ

0.16

odd

0.16

abeth

0.16

nor

0.15

 Ð²ÑģÑĤ

0.15

olars

0.15

Activations Density 0.048%

phrases indicating tasks or processes that are described as easy or simple

No Comments

No Known Activations