INDEX

Explanations

phrases indicating responsibility and expectations in communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

rove

-0.20

iaux

-0.16

antaged

-0.14

udent

-0.14

stad

-0.14

assert

-0.14

wan

-0.14

ofi

-0.14

neau

-0.14

ĶåĽŀ

-0.13

POSITIVE LOGITS

 according

0.15

"[

0.15

 “[

0.15

eldig

0.15

ÐµÐ»Ð¸

0.14

 says

0.14

 According

0.14

Activations Density 0.198%

phrases indicating responsibility and expectations in communication

No Comments

No Known Activations