INDEX

Explanations

instances of the word "more."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 well

-0.21

 bien

-0.19

 Well

-0.19

 more

-0.18

aign

-0.17

well

-0.16

FAR

-0.16

Ø§Ø¨ÙĤÙĩ

-0.15

Well

-0.15

Yao

-0.15

POSITIVE LOGITS

 often

0.22

 completely

0.22

-so

0.21

 readily

0.20

 times

0.20

 string

0.19

 fully

0.19

 frequently

0.19

-read

0.19

often

0.18

Activations Density 0.035%

instances of the word "more."

No Comments

No Known Activations