INDEX

Explanations

phrases indicating expectations or anticipations related to upcoming events or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 given

-0.16

hausen

-0.15

oÅ¡

-0.14

elmet

-0.14

aroo

-0.14

illian

-0.14

Ä±

-0.14

given

-0.13

æĤ

-0.13

eteria

-0.13

POSITIVE LOGITS

 Expect

0.35

 expect

0.35

expect

0.33

Expect

0.33

 expectation

0.33

 expectations

0.32

EXPECT

0.29

_expect

0.28

 EXPECT

0.28

 expecting

0.28

Activations Density 0.104%

phrases indicating expectations or anticipations related to upcoming events or experiences

No Comments

No Known Activations