INDEX

Explanations

phrases that indicate frequency or repetition of events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Ì£

-0.16

.scalablytyped

-0.16

paged

-0.15

Ø±ÙĬÙĥÙĬØ©

-0.14

shed

-0.14

 áº

-0.14

iou

-0.14

ease

-0.14

æ¬¡

-0.14

ìĿ´ìĹĲ

-0.14

POSITIVE LOGITS

 blue

0.29

 awhile

0.27

 Blue

0.25

blue

0.25

-blue

0.23

 BLUE

0.23

Blue

0.23

BLUE

0.22

aw

0.21

.blue

0.21

Activations Density 0.014%

phrases that indicate frequency or repetition of events

No Comments

No Known Activations