INDEX

Explanations

expressions of satisfaction or contentment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

rous

-0.16

å¹¹ç·ļ

-0.15

ouch

-0.14

riv

-0.14

ic

-0.14

sha

-0.14

/format

-0.14

hea

-0.13

tainment

-0.13

iej

-0.13

POSITIVE LOGITS

anter

0.17

 DataContext

0.15

nila

0.14

gMaps

0.14

ardy

0.14

 EntityState

0.14

 Ã©c

0.14

endor

0.14

.hasMore

0.14

weathermap

0.14

Activations Density 0.003%

expressions of satisfaction or contentment

No Comments

No Known Activations