INDEX

Explanations

phrases that indicate methods or approaches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

irs

-0.15

-0.14

ilo

-0.14

ÙĤØ§Ùħ

-0.14

edBy

-0.14

.ov

-0.13

=-=-=-=-

-0.13

Formats

-0.13

byname

-0.13

POSITIVE LOGITS

way

0.33

 ways

0.27

to

0.23

Way

0.23

.way

0.21

 Ways

0.20

WAY

0.20

.getOwnProperty

0.18

 forward

0.17

 Äĳá»ĥ

0.17

Activations Density 0.032%

phrases that indicate methods or approaches

No Comments

No Known Activations