INDEX

Explanations

mentions of personal or identifying information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 leagues

-0.17

\uD

-0.16

verage

-0.16

ringe

-0.16

 Balls

-0.15

owell

-0.15

oku

-0.15

èģŀ

-0.15

sworth

-0.15

oux

-0.15

POSITIVE LOGITS

eyn

0.15

ëĭ¹

0.15

elper

0.15

Ã©nÃ©

0.15

é¢

0.14

Ĥ

0.14

.ads

0.14

è¡

0.14

endoza

0.13

esl

0.13

Activations Density 0.008%

mentions of personal or identifying information

No Comments

No Known Activations