INDEX

Explanations

commas in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

chen

-0.15

yd

-0.15

³

-0.14

RP

-0.14

woo

-0.14

yy

-0.14

ns

-0.14

ÑīÐ¸Ð½

-0.14

ACS

-0.13

jong

-0.13

POSITIVE LOGITS

 ØŃÚ©

0.16

abis

0.15

PageIndex

0.14

Ð¸ÑĤÐ¾Ð²

0.14

ternet

0.14

amel

0.14

.semantic

0.14

cmp

0.14

javax

0.13

age

0.13

Activations Density 0.038%

commas in a document

No Comments

No Known Activations