INDEX

Explanations

HTML tags and elements in a document

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 MatSnackBar

-0.17

 meanwhile

-0.14

Insensitive

-0.14

 Clips

-0.14

laÄį

-0.14

/r

-0.14

minster

-0.14

ÑĤÑĥÑĢ

-0.13

 satisfaction

-0.13

 Meanwhile

-0.13

POSITIVE LOGITS

ECH

0.16

.netbeans

0.15

ãĤ¡

0.15

ãĥ©ãĤ¯

0.15

 CONSEQUENTIAL

0.14

ENCIL

0.14

fruit

0.14

zon

0.14

ziel

0.14

ARING

0.14

Activations Density 0.015%

HTML tags and elements in a document

No Known Activations