INDEX

Explanations

terms associated with historical tours and educational experiences related to significant events and locations

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

æĮ

-0.16

-Allow

-0.15

 nÃ©t

-0.15

kiem

-0.15

ÑĢÐµÑģ

-0.15

ooth

-0.15

ucz

-0.15

 Matth

-0.15

conn

-0.14

Ub

-0.14

POSITIVE LOGITS

ansi

0.16

avir

0.15

cent

0.14

 Enter

0.14

cke

0.13

ped

0.13

ilog

0.13

uell

0.13

 travelers

0.13

 Fore

0.13

Activations Density 0.092%

terms associated with historical tours and educational experiences related to significant events and locations

No Comments

No Known Activations