INDEX

Explanations

punctuation marks and parentheses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Ã¡mara

-0.16

bes

-0.14

 stab

-0.14

ption

-0.14

icha

-0.14

ativity

-0.14

pow

-0.13

 camp

-0.13

 Mahm

-0.13

 Pollution

-0.13

POSITIVE LOGITS

ingroup

0.16

 Benton

0.15

odv

0.14

vant

0.14

³

0.14

xz

0.14

 miÃªu

0.14

ImageContext

0.13

IMS

0.13

otti

0.13

Activations Density 0.056%

punctuation marks and parentheses

No Comments

No Known Activations