INDEX

Explanations

phrases related to choice and alternatives

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

 nejen

-0.23

 both

-0.22

 bÃ¥de

-0.21

 firstly

-0.20

 zwar

-0.17

 kromÄĽ

-0.16

 neither

-0.15

åıĬåħ¶

-0.15

both

-0.15

 everywhere

-0.15

POSITIVE LOGITS

 otherwise

0.27

otherwise

0.23

 else

0.23

 sonst

0.23

 other

0.23

 OTHERWISE

0.22

 simply

0.22

 altogether

0.22

someone

0.21

 simplement

0.21

Activations Density 0.493%

phrases related to choice and alternatives

No Comments

No Known Activations