INDEX

Explanations

phrases indicating transactions or exchanges involving multiple parties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

antan

-0.16

linger

-0.15

ols

-0.15

Fro

-0.15

 NavParams

-0.15

ighth

-0.14

oldt

-0.14

icken

-0.14

 HÃ¼s

-0.14

 factor

-0.14

POSITIVE LOGITS

 audiences

0.22

 opportunity

0.21

eer

0.18

 audience

0.18

 opportunities

0.17

 Audience

0.17

uhl

0.16

ipi

0.16

 away

0.16

Â¯ÃĤ

0.16

Activations Density 0.018%

phrases indicating transactions or exchanges involving multiple parties

No Comments

No Known Activations