INDEX

Explanations

phrases indicating changes in status or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

/Dk

-0.19

ulls

-0.15

 Laden

-0.14

issance

-0.14

ForResource

-0.14

oldown

-0.13

ipple

-0.13

:"-"`↵

-0.13

ottes

-0.13

chwitz

-0.13

POSITIVE LOGITS

 during

0.19

ont

0.17

 when

0.15

efe

0.15

sk

0.15

avo

0.14

"in

0.14

0.13

 significance

0.13

Ð»ÐµÐºÑģÐ°Ð½Ð´

0.13

Activations Density 0.619%

phrases indicating changes in status or conditions

No Comments

No Known Activations