INDEX

Explanations

instances of the word "to."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ato

-0.15

ä»Ķ

-0.14

 lain

-0.14

YA

-0.14

antine

-0.13

Ni

-0.13

Kah

-0.13

HCI

-0.13

Yak

-0.13

uros

-0.13

POSITIVE LOGITS

ÅĽ

0.20

forums

0.15

/*č↵

0.15

ought

0.15

oyer

0.14

zer

0.14

ward

0.14

à¥ģà¤§

0.14

Ã¼zel

0.14

otics

0.14

Activations Density 0.009%

instances of the word "to."

No Comments

No Known Activations