INDEX

Explanations

references to geographic locations and communities

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

 eldre

-0.17

"value

-0.17

 Acres

-0.16

outil

-0.15

chwitz

-0.14

essian

-0.14

íĥķ

-0.14

.Rad

-0.14

untu

-0.14

ATAB

-0.14

POSITIVE LOGITS

uter

0.16

abel

0.16

opy

0.15

-abs

0.15

abs

0.15

NEL

0.15

 turnover

0.15

rant

0.14

au

0.14

Activations Density 0.011%

references to geographic locations and communities

No Comments

No Known Activations