INDEX

Explanations

the word "as" in various contexts and patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

owards

-0.16

 part

-0.14

-away

-0.14

 oldukÃ§a

-0.14

lobals

-0.14

imore

-0.13

 Extremely

-0.13

erta

-0.13

 awhile

-0.13

such

-0.12

POSITIVE LOGITS

if

0.48

 though

0.38

if

0.28

 ÐµÑģÐ»Ð¸

0.26

though

0.26

 náº¿u

0.26

 Though

0.25

If

0.25

Though

0.23

 wenn

0.23

Activations Density 0.132%

the word "as" in various contexts and patterns

No Comments

No Known Activations