INDEX

Explanations

punctuation marks, especially exclamation points and periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ãģ¯ãģļ

-0.17

gnore

-0.15

æŃ£

-0.13

âĢĥ

-0.13

ramid

-0.13

 Ø¢Ø®Ø±ÛĮÙĨ

-0.13

Dou

-0.13

ãģĹãģı

-0.13

(*(

-0.13

POSITIVE LOGITS

0.40

0.28

Û±

0.24

ï¼ĳ

0.24

âĳł

0.20

âĦĸ

0.18

âĤģ

0.18

âĸį

0.17

anik

0.16

 firstly

0.16

Activations Density 0.081%

punctuation marks, especially exclamation points and periods

No Comments

No Known Activations