INDEX

Explanations

technical terms and concepts related to engineering and physics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

artz

-0.18

ç¢¼

-0.16

 Â§Â§

-0.15

ODEV

-0.15

ł

-0.14

å©Ĩ

-0.14

ÃĹ

-0.14

reh

-0.14

 ëĭ¤ìļ´ë°Ľê¸°

-0.14

 Â§

-0.13

POSITIVE LOGITS

/=

0.19

/(

0.17

lim

0.17

tan

0.17

 Failed

0.16

0.15

 Tout

0.15

.getOwnProperty

0.15

linger

0.15

exp

0.15

Activations Density 0.269%

technical terms and concepts related to engineering and physics

No Comments

No Known Activations