INDEX

Explanations

phrases indicating the need or necessity for something

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ç¨ĭ

-0.15

 Harvey

-0.15

reen

-0.15

ren

-0.14

ardy

-0.14

avy

-0.14

 ãĥĶ

-0.14

mbH

-0.14

sters

-0.14

POSITIVE LOGITS

pler

0.16

istor

0.16

ocate

0.15

[](

0.15

 Mall

0.15

_FP

0.15

modifiable

0.14

acente

0.14

Ð½ÐµÑĤ

0.14

ëıĻ

0.13

Activations Density 0.009%

phrases indicating the need or necessity for something

No Comments

No Known Activations