INDEX

Explanations

phrases indicating uncertainty or hypothetical situations

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

 opat

-0.16

istas

-0.15

usch

-0.15

reports

-0.14

Äįet

-0.14

({_

-0.14

Å¡et

-0.13

istik

-0.13

ylan

-0.13

unta

-0.13

POSITIVE LOGITS

because

0.21

 because

0.21

Because

0.21

 Ð¿Ð¾ÑĤÐ¾Ð¼Ñĥ

0.20

 Because

0.20

 porque

0.20

ecause

0.19

you

0.19

""

0.19

 number

0.18

Activations Density 0.174%

phrases indicating uncertainty or hypothetical situations

No Comments

No Known Activations