INDEX

Explanations

dates and time-related information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ople

-0.16

Ã©m

-0.15

umont

-0.15

 Manning

-0.15

erg

-0.15

ç¯ī

-0.15

chner

-0.14

POSITIVE LOGITS

0.16

tery

0.16

ua

0.16

æľĢæĸ°

0.16

 bidi

0.15

wed

0.15

Ø§Ùĩ

0.15

ked

0.14

jsonp

0.14

COVID

0.14

Activations Density 0.092%

dates and time-related information

No Comments

No Known Activations