INDEX

Explanations

references to health-related topics and organizations

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

Ã¼p

-0.15

minster

-0.14

SEN

-0.14

ynn

-0.14

olt

-0.14

 Milton

-0.13

Doctrine

-0.13

arya

-0.13

POSITIVE LOGITS

enheim

0.17

essler

0.17

strand

0.15

icz

0.14

CEL

0.14

ãĥ¼ãĥĩ

0.14

raki

0.14

 Gale

0.14

æ·±

0.14

_CHANNELS

0.14

Activations Density 0.152%

references to health-related topics and organizations

No Comments

No Known Activations