INDEX

Explanations

adjectives that convey significance, intensity, or danger

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

Ã©r

-0.16

zt

-0.16

aro

-0.15

enza

-0.14

Ã¨res

-0.14

anske

-0.14

://{

-0.14

imid

-0.13

athers

-0.13

azel

-0.13

POSITIVE LOGITS

 imaginable

0.26

of

0.25

yet

0.24

-ever

0.22

yet

0.22

 possible

0.21

possible

0.21

 aspects

0.21

Yet

0.20

 aspect

0.20

Activations Density 0.078%

adjectives that convey significance, intensity, or danger

No Comments

No Known Activations