INDEX

Explanations

the word "where" in various contexts related to locations and situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ly

-0.16

elig

-0.16

them

-0.15

aches

-0.15

ëį°

-0.15

SearchParams

-0.15

scan

-0.14

zen

-0.14

erals

-0.14

/we

-0.14

POSITIVE LOGITS

upon

0.33

abouts

0.27

fore

0.24

ver

0.24

of

0.23

unto

0.22

VER

0.22

-Ð½Ð¸Ð±ÑĥÐ´ÑĮ

0.22

on

0.21

ever

0.20

Activations Density 0.074%

the word "where" in various contexts related to locations and situations

No Comments

No Known Activations