INDEX

Explanations

phrases that express personal opinions or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

amburger

-0.16

.utf

-0.15

 Ð½Ð°ÑģÑĤ

-0.15

ahat

-0.14

urm

-0.14

alse

-0.14

ÄĻ

-0.14

alleng

-0.13

atan

-0.13

èĺ

-0.13

POSITIVE LOGITS

fortunate

0.15

osis

0.15

 attribute

0.14

ŀæĢ§

0.14

_cli

0.14

-uri

0.14

 Complaint

0.14

agger

0.13

 deliberate

0.13

 intentional

0.13

Activations Density 0.142%

phrases that express personal opinions or evaluations

No Comments

No Known Activations