INDEX

Explanations

phrases indicating successful outcomes or results in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

locker

-0.15

ENSITY

-0.15

yle

-0.14

onical

-0.14

aepernick

-0.13

iw

-0.13

llib

-0.13

 Ø¹ÙĪØ§ÙħÙĦ

-0.13

uso

-0.13

onus

-0.13

POSITIVE LOGITS

 increased

0.24

 further

0.22

 greater

0.21

 decreased

0.21

 eventual

0.20

vely

0.18

an

0.18

 overall

0.17

 corresponding

0.17

Activations Density 0.133%

phrases indicating successful outcomes or results in various contexts

No Comments

No Known Activations