INDEX

Explanations

phrases indicating removal or separation

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

 viá»ĩn

-0.16

OperationException

-0.15

#ac

-0.15

htub

-0.15

reverse

-0.14

áºŃt

-0.14

 Reverse

-0.14

.fm

-0.14

uant

-0.14

zos

-0.14

POSITIVE LOGITS

 beaten

0.33

bat

0.31

 cuff

0.30

 mark

0.27

 grid

0.25

 hook

0.25

 charts

0.24

bat

0.24

 radar

0.22

 wall

0.22

Activations Density 0.017%

phrases indicating removal or separation

No Comments

No Known Activations