INDEX

Explanations

programming-related terms and syntax

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

 Bren

-0.14

 Beard

-0.14

 Cyrus

-0.13

 æĴ

-0.13

Mog

-0.13

.simps

-0.12

ado

-0.12

drag

-0.12

 Grip

-0.12

æıĴ

-0.12

POSITIVE LOGITS

 corpor

0.29

 Corpor

0.28

 word

0.28

 train

0.28

 sentences

0.26

 sent

0.26

 SENT

0.26

 Sent

0.25

 Train

0.24

 Token

0.24

Activations Density 0.027%

programming-related terms and syntax

No Comments

No Known Activations