INDEX

Explanations

expressions of gratitude or acknowledgment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

.grad

-0.14

itore

-0.14

Mailer

-0.14

illow

-0.14

ML

-0.14

ÑģÑĤÑĮ

-0.14

angen

-0.14

MLS

-0.14

 Fruit

-0.13

ML

-0.13

POSITIVE LOGITS

annes

0.17

tvrt

0.16

ione

0.15

iente

0.14

 Cursors

0.14

bei

0.13

ursors

0.13

eger

0.13

Å¯v

0.13

æ´¥

0.13

Activations Density 0.259%

expressions of gratitude or acknowledgment

No Comments

No Known Activations