INDEX

Explanations

mentions of the word "since."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

Ã¡o

-0.15

ProgressHUD

-0.15

imin

-0.15

vise

-0.15

geois

-0.14

deaux

-0.14

hiba

-0.14

uling

-0.14

ëħĦìĹĲ

-0.14

 jiÅ¾

-0.14

POSITIVE LOGITS

 before

0.30

before

0.23

 shortly

0.21

 BEFORE

0.21

 being

0.21

 antes

0.20

 Before

0.20

 they

0.19

-before

0.19

Before

0.19

Activations Density 0.042%

mentions of the word "since."

No Comments

No Known Activations