INDEX

Explanations

instances of the article "an" used 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

gaard

-0.14

auss

-0.14

auf

-0.14

 baÅŁÄ±na

-0.13

.pb

-0.13

atin

-0.13

antic

-0.13

gil

-0.13

kÃ¶

-0.13

POSITIVE LOGITS

ther

0.29

archy

0.18

iling

0.18

ony

0.17

thers

0.17

ointed

0.17

esthetic

0.16

imes

0.15

/the

0.15

Ð¶Ð¸

0.15

Activations Density 0.238%

instances of the article "an" used in various contexts

No Comments

No Known Activations