INDEX

Explanations

phrases indicating importance or emphasis 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 @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Ì§

-0.17

cona

-0.17

amble

-0.16

endor

-0.16

-0.15

ContentSize

-0.15

usk

-0.15

glas

-0.15

ynamo

-0.14

ãĤ¤ãĤ¯

-0.14

POSITIVE LOGITS

 ÙĪÛĮÚĺÙĩ

0.15

Ord

0.15

lias

0.15

od

0.14

arging

0.14

-Requested

0.14

uptools

0.14

ord

0.14

CDF

0.14

zaz

0.14

Activations Density 0.079%

phrases indicating importance or emphasis in the text

No Comments

No Known Activations