INDEX

Explanations

references to "world" in various contexts, indicating a focus on global or universal themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

elor

-0.18

eters

-0.16

ases

-0.16

imson

-0.16

Ã¡bado

-0.14

atures

-0.14

imap

-0.14

è¼Ŀ

-0.14

mons

-0.14

oter

-0.13

POSITIVE LOGITS

-wide

0.30

liness

0.26

Wide

0.25

wide

0.24

 wide

0.23

views

0.23

 Wide

0.22

-ren

0.19

/world

0.18

Ú¯ÛĮØ±

0.17

Activations Density 0.094%

references to "world" in various contexts, indicating a focus on global or universal themes

No Comments

No Known Activations