INDEX

Explanations

phrases that describe negative consequences or impacts of various actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Ø¯ÙĬØ«

-0.15

endid

-0.14

icina

-0.14

NSBundle

-0.14

 ÑĩÑĤÐ¾Ð±Ñĭ

-0.14

onian

-0.14

 inorder

-0.13

ÙĨØ¯Ø§ÙĨ

-0.13

åĭĻ

-0.13

Å¡em

-0.13

POSITIVE LOGITS

 both

0.28

not

0.25

 upon

0.23

both

0.22

/effects

0.20

 felt

0.19

 BOTH

0.19

felt

0.18

 nejen

0.18

 lives

0.17

Activations Density 0.161%

phrases that describe negative consequences or impacts of various actions or events

No Comments

No Known Activations