INDEX

Explanations

phrases related to legal professions and educational backgrounds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

anÃ©

-0.17

gu

-0.16

yne

-0.15

seau

-0.14

ovol

-0.14

aniem

-0.14

orses

-0.14

..

-0.14

orf

-0.13

gu

-0.13

POSITIVE LOGITS

0.29

0.20

Û²Û°Û±

0.19

0.17

¶ģ

0.15

 Deniz

0.15

«ĺ

0.15

ousel

0.15

 INTERRUPTION

0.15

Activations Density 0.165%

phrases related to legal professions and educational backgrounds

No Comments

No Known Activations