INDEX

Explanations

repeated actions or statements in the text

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

vic

-0.16

*>*

-0.15

cket

-0.15

raci

-0.14

ëĿ¼ëıĦ

-0.14

vie

-0.14

Ì£

-0.14

rick

-0.14

ÑĨÐµÐ·

-0.14

POSITIVE LOGITS

 throughout

0.19

 whenever

0.16

 Kirby

0.14

 lately

0.14

 proved

0.14

Ð°ÑİÑĤ

0.13

Kir

0.13

 wherever

0.13

oons

0.13

 repeatedly

0.13

Activations Density 0.152%

repeated actions or statements in the text

No Comments

No Known Activations

repeated actions or statements in the text

No Comments

No Known Activations