INDEX

Explanations

phrases related to searching for or discovering information

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

anki

-0.14

Ã¹

-0.14

izo

-0.14

azzi

-0.14

-Up

-0.14

uzzi

-0.14

 voks

-0.14

åĥį

-0.14

UP

-0.13

Viewport

-0.13

POSITIVE LOGITS

 find

0.42

 Find

0.36

Find

0.33

-find

0.32

 finds

0.32

 FIND

0.32

 found

0.32

find

0.30

 finding

0.29

.find

0.29

Activations Density 0.021%

phrases related to searching for or discovering information

No Comments

No Known Activations