INDEX

Explanations

elements related to user interface or component attributes in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ATAR

-0.18

illac

-0.17

ollow

-0.17

STYLE

-0.17

Ã¡st

-0.17

oha

-0.17

agal

-0.15

imore

-0.15

-uppercase

-0.15

Ð»ÐµÑĤ

-0.15

POSITIVE LOGITS

0.18

 flex

0.17

sm

0.17

ire

0.16

 wire

0.16

 Chandler

0.16

 NEXT

0.16

kyt

0.15

 classNames

0.15

Activations Density 0.004%

elements related to user interface or component attributes in code

No Comments

No Known Activations