INDEX

Explanations

concepts and terms related to legality and rules 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 @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ãĥ¼ãĥĢ

-0.17

hi

-0.17

äº

-0.16

instead

-0.16

ude

-0.15

ãĤ©

-0.14

Milliseconds

-0.14

ãĤ·ãĤ¢

-0.13

 Martial

-0.13

blr

-0.13

POSITIVE LOGITS

 except

0.29

 unless

0.25

 PROVIDED

0.25

 provided

0.24

 Except

0.24

 limited

0.23

 certain

0.22

 Provided

0.22

except

0.22

if

0.21

Activations Density 0.435%

concepts and terms related to legality and rules in various contexts

No Comments

No Known Activations