INDEX

Explanations

phrases indicating a state of activity or fullness

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

ATS

-0.18

ibbon

-0.16

iser

-0.15

ats

-0.15

pip

-0.14

gard

-0.14

rink

-0.14

isers

-0.14

serter

-0.14

POSITIVE LOGITS

 gear

0.38

 full

0.31

 swing

0.27

 mode

0.26

 Gear

0.25

gear

0.24

Gear

0.24

 warp

0.24

 gears

0.23

 hyper

0.22

Activations Density 0.055%

phrases indicating a state of activity or fullness

No Comments

No Known Activations