INDEX

Explanations

terms and phrases related to academic and professional classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

’m

-0.18

zew

-0.17

ighbor

-0.15

omb

-0.15

ollapsed

-0.14

Ã½v

-0.14

ToFit

-0.14

 wasn

-0.13

readystatechange

-0.13

Bounding

-0.13

POSITIVE LOGITS

are

0.67

_are

0.53

are

0.51

ARE

0.49

 aren

0.47

Are

0.46

Are

0.45

.are

0.44

 were

0.42

 ÙĩØ³ØªÙĨØ¯

0.41

Activations Density 0.513%

terms and phrases related to academic and professional classifications

No Comments

No Known Activations