INDEX

Explanations

formal statements and discussions related to policy, research, and critical analysis

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

antage

-0.14

landers

-0.14

 Stateless

-0.14

ound

-0.14

alone

-0.14

-ci

-0.14

ontent

-0.14

ervers

-0.14

cores

-0.13

adow

-0.13

POSITIVE LOGITS

of

0.14

éĿ©

0.14

daki

0.14

 ëĶ°ë¥¸

0.14

anden

0.14

ForResult

0.13

zum

0.13

OMUX

0.13

 à¤ĳà¤«

0.13

unknown

0.13

Activations Density 0.228%

formal statements and discussions related to policy, research, and critical analysis

No Comments

No Known Activations