INDEX

Explanations

geographical locations and cities mentioned in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

atte

-0.17

baugh

-0.16

uzzi

-0.16

ipo

-0.15

gor

-0.14

Mog

-0.14

IDI

-0.14

Î»ÎµÏħ

-0.14

idd

-0.13

.setProperty

-0.13

POSITIVE LOGITS

.scalablytyped

0.18

oux

0.15

 defaultManager

0.14

ernals

0.14

LEGRO

0.14

âĹĨ

0.14

xca

0.14

ICK

0.13

 MERCHANTABILITY

0.13

apos

0.13

Activations Density 0.052%

geographical locations and cities mentioned in the text

No Comments

No Known Activations