INDEX

Explanations

phrases related to quality and effectiveness in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ARGS

-0.15

ollower

-0.14

-lfs

-0.14

hle

-0.14

allo

-0.13

jec

-0.13

 Inspiration

-0.13

ãĥ«ãĥī

-0.13

ndx

-0.13

 TakÄ±m

-0.13

POSITIVE LOGITS

way

0.34

 effective

0.29

 sure

0.28

 great

0.27

 excellent

0.25

 proven

0.25

 smart

0.24

Win

0.23

Way

0.23

win

0.23

Activations Density 0.132%

phrases related to quality and effectiveness in various contexts

No Comments

No Known Activations

phrases related to quality and effectiveness in various contexts

No Comments

No Known Activations