INDEX

Explanations

collaborative efforts and teamwork

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Ã¼gen

-0.15

 tract

-0.14

dic

-0.14

amac

-0.14

nty

-0.14

arrass

-0.13

arshal

-0.13

 Ulus

-0.13

 trig

-0.13

CEE

-0.13

POSITIVE LOGITS

 jadx

0.17

etz

0.16

andro

0.16

finger

0.15

-peer

0.15

hips

0.15

iek

0.14

iesen

0.14

 forces

0.14

æİĮ

0.14

Activations Density 0.006%

collaborative efforts and teamwork

No Comments

No Known Activations