INDEX

Explanations

punctuation marks and formatting within 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 @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

fÃ¼g

-0.17

Smy

-0.15

intr

-0.15

ulado

-0.14

StackNavigator

-0.14

ÐµÑĢÐ°Ð»ÑĮ

-0.14

LY

-0.14

isko

-0.14

izr

-0.13

occo

-0.13

POSITIVE LOGITS

Tao

0.15

xies

0.14

 {{↵

0.14

anta

0.14

 blues

0.14

elin

0.14

elden

0.14

 <!--[

0.13

ĺ

0.13

.intellij

0.13

Activations Density 0.496%

punctuation marks and formatting within the text

No Comments

No Known Activations