INDEX

Explanations

instances of the word "on."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

è¢ĭ

-0.15

Spread

-0.15

ambi

-0.15

 Pent

-0.15

ysi

-0.15

èĿ

-0.14

ily

-0.14

Ø¯Ø§Ø±

-0.14

æ¹¯

-0.14

fty

-0.14

POSITIVE LOGITS

areth

0.16

oltip

0.16

Insensitive

0.15

iao

0.14

odyn

0.14

ackbar

0.14

cred

0.14

 behalf

0.13

¨

0.13

Activations Density 0.113%

instances of the word "on."

No Comments

No Known Activations