INDEX

Explanations

attributes related to size and strength in various contexts

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

New Auto-Interp

Configuration

fnlp/Llama3_1-8B-Base-LXM-8x/Llama3_1-8B-Base-L22M-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_mlp_out

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

 Petite

-0.17

cko

-0.16

ptune

-0.15

hazi

-0.15

anvas

-0.15

 Little

-0.15

pane

-0.14

OG

-0.14

leri

-0.14

INTR

-0.14

POSITIVE LOGITS

 strong

0.45

big

0.44

 large

0.41

 tall

0.35

 loud

0.34

big

0.34

large

0.31

 wide

0.30

 fast

0.29

.big

0.27

Activations Density 0.863%

attributes related to size and strength in various contexts

No Comments

No Known Activations