INDEX

Explanations

references to royal institutions and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

åĿĬ

-0.16

ocket

-0.15

ixo

-0.14

Ð¾ÑĪ

-0.14

éĩı

-0.14

yaw

-0.14

ultimate

-0.14

adu

-0.14

REFER

-0.13

POSITIVE LOGITS

zed

0.19

ised

0.18

ized

0.18

izing

0.18

isation

0.16

ises

0.15

izes

0.15

ization

0.15

son

0.15

adder

0.14

Activations Density 0.017%

references to royal institutions and titles

No Comments

No Known Activations