INDEX

Explanations

phrases that introduce lists or examples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

eyer

-0.16

è¿Ļä¸Ģ

-0.14

 determinant

-0.14

ancy

-0.14

ze

-0.14

these

-0.14

 Illustr

-0.13

 THIS

-0.13

 Intermediate

-0.13

this

-0.13

POSITIVE LOGITS

 some

0.24

 links

0.19

some

0.18

Links

0.17

 Ø¨Ø±Ø®ÛĮ

0.17

(links

0.17

-links

0.16

links

0.16

 several

0.15

 Some

0.15

Activations Density 0.034%

phrases that introduce lists or examples

No Comments

No Known Activations