INDEX

Explanations

phrases emphasizing the concept of importance and significance across 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 @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

iers

-0.17

ylie

-0.15

orado

-0.14

ucas

-0.14

ãĥ¼ãĤ¹

-0.14

yang

-0.14

á»Ľi

-0.14

 will

-0.14

akk

-0.13

AAAA

-0.13

POSITIVE LOGITS

 importance

0.18

 Importance

0.16

ivet

0.15

angler

0.15

uong

0.15

caffold

0.14

\grid

0.14

ë¡

0.14

edy

0.14

andom

0.14

Activations Density 0.039%

phrases emphasizing the concept of importance and significance across various contexts

No Comments

No Known Activations