INDEX

Explanations

intensifiers, specifically the word "very" and similar expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

oris

-0.15

ÑģÑĤÑİ

-0.15

embre

-0.15

Ð¾ÑĢÑıÐ´

-0.14

hti

-0.14

orre

-0.14

exter

-0.14

curacy

-0.14

Ã¡ly

-0.14

\Migrations

-0.14

POSITIVE LOGITS

 same

0.20

0.19

 thing

0.18

same

0.17

 SAME

0.17

 essence

0.16

tons

0.16

ewan

0.16

 opposite

0.15

Activations Density 0.018%

intensifiers, specifically the word "very" and similar expressions

No Comments

No Known Activations