INDEX

Explanations

phrases related to historical or regulatory frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

but

-0.18

 Ã§Ã¼nkÃ¼

-0.16

BUT

-0.15

èĢĮ

-0.15

but

-0.15

 thereby

-0.15

iar

-0.15

{}.

-0.15

 takÅ¾e

-0.14

ÎºÎ¹

-0.14

POSITIVE LOGITS

 unlike

0.26

 like

0.26

 along

0.22

along

0.20

 together

0.19

 Unlike

0.17

 once

0.17

 Like

0.17

 while

0.17

 despite

0.17

Activations Density 0.239%

phrases related to historical or regulatory frameworks

No Comments

No Known Activations