INDEX

Explanations

punctuation marks, particularly periods and exclamation points

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

-0.15

 Same

-0.14

 Strange

-0.14

 Crazy

-0.14

ä»¤

-0.14

echa

-0.14

dif

-0.14

’

-0.13

time

-0.13

POSITIVE LOGITS

atsu

0.17

 ç²

0.16

.chapter

0.14

abic

0.14

èª¬

0.14

Rgb

0.14

ãģĤãĤĬãģĮãģ¨ãģĨãģĶãģĸ

0.14

CHAPTER

0.14

ãĤ¤ãĤ¯

0.13

Ð»Ð¾Ð¿

0.13

Activations Density 0.001%

punctuation marks, particularly periods and exclamation points

No Comments

No Known Activations