INDEX

Explanations

phrases that indicate comparisons or contrasting ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

inous

-0.15

TECTED

-0.14

.xhtml

-0.14

tes

-0.13

 (),↵

-0.13

uzu

-0.13

à¸ļà¸²à¸¢

-0.13

ardless

-0.13

Ã¼h

-0.13

atcher

-0.13

POSITIVE LOGITS

 latter

1.61

 Latter

0.72

 former

0.61

 later

0.58

former

0.49

 Later

0.45

later

0.44

 Former

0.44

Later

0.43

Former

0.41

Activations Density 0.287%

phrases that indicate comparisons or contrasting ideas

No Comments

No Known Activations