INDEX

Explanations

elements related to user interface interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Dirt

-0.17

eton

-0.16

Ð½ÐºÐ°

-0.15

.tell

-0.15

ichel

-0.14

éĭ

-0.14

asad

-0.14

.DialogResult

-0.14

raci

-0.14

Ø¨Ø±ÛĮ

-0.14

POSITIVE LOGITS

 drop

0.39

-drop

0.35

dro

0.34

drop

0.33

dro

0.32

 Drop

0.31

.drop

0.30

_drop

0.29

Drop

0.29

 drops

0.28

Activations Density 0.033%

elements related to user interface interactions

No Comments

No Known Activations