INDEX

Explanations

phrases related to evaluation and comparative analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

but

-0.28

omo

-0.22

 however

-0.20

ellar

-0.18

 aber

-0.18

 nhÆ°ng

-0.18

but

-0.18

But

-0.17

 maar

-0.17

ä½Ĩ

-0.17

POSITIVE LOGITS

isku

0.15

#ab

0.14

baugh

0.14

Ð¾Ñĥ

0.14

Ð¾Ð»Ð¾Ð¶

0.13

stadt

0.13

 nonetheless

0.13

è¿ĺæĺ¯

0.13

utory

0.13

å½

0.13

Activations Density 0.061%

phrases related to evaluation and comparative analysis

No Comments

No Known Activations