INDEX

Explanations

assertions or claims about proving something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

/small

-0.17

 Westbrook

-0.16

/or

-0.15

quate

-0.14

.fil

-0.14

ropolitan

-0.14

plane

-0.14

ãĥ¼ãĤ¹ãĥĪ

-0.13

Ð¾Ð±ÑĢÐ°Ð

-0.13

upon

-0.13

POSITIVE LOGITS

ë£¹

0.15

Narrated

0.14

hra

0.14

ultz

0.14

baar

0.14

Æ¯á»

0.14

eÄį

0.14

ItemClick

0.14

eed

0.14

bia

0.14

Activations Density 0.038%

assertions or claims about proving something

No Comments

No Known Activations