INDEX

Explanations

images and numerical data related to products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.15

rio

-0.14

jen

-0.14

anks

-0.14

iforn

-0.14

fÃ¶r

-0.13

"';

-0.13

.foundation

-0.13

rios

-0.13

POSITIVE LOGITS

0.47

0.36

0.28

0.27

0.25

0.24

0.23

Û¹

0.23

Activations Density 0.036%

images and numerical data related to products

No Comments

No Known Activations