INDEX

Explanations

occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

èħ

-0.18

olin

-0.16

ilogy

-0.15

breadcrumbs

-0.15

fov

-0.15

Ã¤ch

-0.15

riangle

-0.15

åħ¥åı£

-0.14

owied

-0.14

olina

-0.14

POSITIVE LOGITS

 behalf

0.45

 heels

0.31

eve

0.31

 occasion

0.30

 basis

0.28

 verge

0.26

 occasions

0.25

basis

0.24

occasion

0.21

 heals

0.21

Activations Density 0.141%

occurrences of the word "the."

No Comments

No Known Activations