INDEX

Explanations

structured data and detailed instructions related to processes or guidelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ahren

-0.17

jis

-0.15

ulp

-0.15

chine

-0.14

pron

-0.14

ìĶ

-0.14

li

-0.14

igma

-0.13

raise

-0.13

ombat

-0.13

POSITIVE LOGITS

 migrationBuilder

0.15

)NULL

0.15

.toJSON

0.14

’na

0.14

tor

0.14

ÃľRK

0.14

otts

0.14

åĶĩ

0.14

å¦Ĥä¸ĭ

0.13

Activations Density 0.393%

structured data and detailed instructions related to processes or guidelines

No Comments

No Known Activations