INDEX

Explanations

phrases indicating uncertainty or skepticism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

omore

-0.18

oui

-0.17

Ð¼Ð¾ÑĢ

-0.16

ë¹

-0.15

ixon

-0.14

 HÃ¶

-0.14

 /*#__

-0.13

ãĥĥãĤ¯ãĤ¹

-0.13

eses

-0.13

å·±

-0.13

POSITIVE LOGITS

isz

0.17

 until

0.17

 till

0.16

rtl

0.16

 Franklin

0.15

ierz

0.15

³

0.15

Ø§Ø¦ÙĤ

0.14

à¸²à¸Ķ

0.14

 raised

0.14

Activations Density 0.283%

phrases indicating uncertainty or skepticism

No Comments

No Known Activations