INDEX

Explanations

phrases that indicate an introduction or overview of content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

-0.15

ne

-0.15

verbose

-0.14

 norm

-0.14

abar

-0.14

igsaw

-0.14

 behand

-0.13

.rule

-0.13

 arou

-0.13

POSITIVE LOGITS

.arraycopy

0.17

ismatic

0.15

Gratis

0.15

 article

0.14

asje

0.14

èİ

0.14

ciÃ³

0.14

ê¶Į

0.14

0.13

åºĵ

0.13

Activations Density 0.061%

phrases that indicate an introduction or overview of content

No Comments

No Known Activations