INDEX

Explanations

references to the term "West" 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

orra

-0.18

odore

-0.17

jang

-0.17

Ð´Ñı

-0.16

ugh

-0.15

ultz

-0.15

quiry

-0.15

etimes

-0.15

quina

-0.14

utor

-0.14

POSITIVE LOGITS

 Coast

0.25

 Indies

0.21

lake

0.21

 coast

0.20

gate

0.20

cott

0.20

ern

0.20

ph

0.20

chester

0.20

 Virginia

0.18

Activations Density 0.017%

references to the term "West" in various contexts

No Comments

No Known Activations