INDEX

Explanations

instances of punctuation or formatting marks in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

arakter

-0.15

å½¹

-0.14

msp

-0.14

/*č↵

-0.13

.TabStop

-0.13

leich

-0.13

mise

-0.12

ãĤ¤ãĥī

-0.12

contres

-0.12

-↵↵

-0.12

POSITIVE LOGITS

is

0.20

has

0.20

are

0.17

can

0.16

 will

0.16

was

0.15

ling

0.15

 cannot

0.15

 could

0.15

 must

0.15

Activations Density 0.149%

instances of punctuation or formatting marks in text

No Comments

No Known Activations