INDEX

Explanations

publication references and citation information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

åĽĽ

-0.17

lÃ©d

-0.15

ï¼Ķ

-0.15

 bá»ĳn

-0.15

../../

-0.14

otti

-0.14

four

-0.14

à¹

-0.14

POSITIVE LOGITS

0.39

two

0.33

äºĮ

0.29

.two

0.29

Feb

0.28

Two

0.28

ï¼Ĵ

0.28

 February

0.28

0.27

zwe

0.27

Activations Density 0.047%

publication references and citation information

No Comments

No Known Activations