INDEX

Explanations

numeric values related to statistics or measurements

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ix

-0.17

riad

-0.15

vid

-0.15

Thr

-0.14

exc

-0.14

 footsteps

-0.14

 Wing

-0.14

eries

-0.13

 _↵

-0.13

wil

-0.13

POSITIVE LOGITS

ambi

0.15

adro

0.14

å¿ĺ

0.14

 sounding

0.14

onne

0.14

atore

0.14

etten

0.14

bject

0.14

ãĥ³ãĤº

0.13

arend

0.13

Activations Density 0.127%

numeric values related to statistics or measurements

No Known Activations