INDEX

Explanations

comparative phrases and contrasts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

<?>>

-0.14

è©²

-0.14

obot

-0.14

.opend

-0.13

zin

-0.13

orris

-0.12

WN

-0.12

WidgetItem

-0.12

 rundown

-0.12

 oltre

-0.12

POSITIVE LOGITS

 Ð²Ð¾ÑĤ

0.23

 Conversely

0.21

 whereas

0.21

 convers

0.21

 counterpart

0.20

 Whereas

0.20

 naopak

0.20

 Ð¶Ðµ

0.19

 Ø£ÙħØ§

0.18

å¯¹äºİ

0.18

Activations Density 0.296%

comparative phrases and contrasts

No Comments

No Known Activations