INDEX

Explanations

phrases indicating ownership or authorship

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

edor

-0.16

à¸¸

-0.14

.addColumn

-0.14

iesen

-0.14

bang

-0.13

 Ø¢Ø²

-0.13

orado

-0.13

uckets

-0.13

åŃ¸éĻ¢

-0.13

LEMENT

-0.13

POSITIVE LOGITS

 engr

0.17

aven

0.15

alfa

0.15

dio

0.14

AFE

0.14

gate

0.14

 Depot

0.14

uyen

0.14

creativecommons

0.14

Activations Density 0.040%

phrases indicating ownership or authorship

No Comments

No Known Activations