INDEX

Explanations

terms related to organizations and organizational structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

umbn

-0.16

peria

-0.15

ÌĢ

-0.14

rott

-0.14

celik

-0.14

Pop

-0.14

orgh

-0.14

adow

-0.14

ghan

-0.14

 Kami

-0.13

POSITIVE LOGITS

-wide

0.17

ynos

0.15

wide

0.15

ÐµÑģÑĤÐ¸

0.15

able

0.14

Ð¢Ðŀ

0.14

.jdesktop

0.14

nel

0.14

 Theresa

0.13

à¸ŀà¸¢

0.13

Activations Density 0.032%

terms related to organizations and organizational structures

No Comments

No Known Activations