INDEX

Explanations

terms related to secondary aspects or considerations in various contexts

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

obar

-0.15

rai

-0.14

ëĤ´ê¸°

-0.14

 chung

-0.14

cheon

-0.14

ervas

-0.14

ÑģÐ¾Ð»

-0.14

affer

-0.14

-eyed

-0.14

æ¶

-0.13

POSITIVE LOGITS

 Wind

0.17

/add

0.16

 wind

0.16

ities

0.15

utherland

0.15

Wind

0.15

CJK

0.15

Zwe

0.15

ello

0.14

jet

0.14

Activations Density 0.122%

terms related to secondary aspects or considerations in various contexts

No Comments

No Known Activations