INDEX

Explanations

phrases indicating correspondence or communication, particularly in professional or formal 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

istrovstvÃŃ

-0.17

wel

-0.15

Tyr

-0.15

lein

-0.14

Err

-0.14

uhn

-0.14

ÑĤÐ¸Ð¹

-0.13

baar

-0.13

oogle

-0.13

Ø§ÙĬØ±

-0.13

POSITIVE LOGITS

attached

0.17

 Attached

0.17

 attached

0.17

Attached

0.17

 enclosed

0.16

 your

0.16

.spi

0.15

Brief

0.14

acre

0.14

 Wins

0.14

Activations Density 0.674%

phrases indicating correspondence or communication, particularly in professional or formal contexts

No Comments

No Known Activations