INDEX

Explanations

numeric values and time-related data

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

New Auto-Interp

Configuration

fnlp/Llama3_1-8B-Base-LXM-8x/Llama3_1-8B-Base-L22M-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_mlp_out

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

Ð±Ð°Ñĩ

-0.18

æ¸

-0.16

inem

-0.15

-tm

-0.15

thest

-0.14

astle

-0.14

holm

-0.13

odont

-0.13

à¸¨à¸²à¸ªà¸ķà¸£

-0.13

POSITIVE LOGITS

izen

0.16

ÑĢÑĥÐ´

0.16

0.15

han

0.15

Çİ

0.15

rea

0.15

<textarea

0.15

º¼

0.15

Subtitle

0.14

Activations Density 0.181%

numeric values and time-related data

No Comments

No Known Activations