INDEX

Explanations

references to specific individuals and their achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

acket

-0.16

acias

-0.15

uling

-0.15

enco

-0.15

Dash

-0.15

ertil

-0.14

unos

-0.14

dust

-0.14

-Sah

-0.14

mlin

-0.14

POSITIVE LOGITS

oct

0.24

 concede

0.24

 conced

0.23

 conf

0.21

oct

0.21

 attrib

0.20

 confer

0.20

off

0.20

 donate

0.20

don

0.19

Activations Density 0.057%

references to specific individuals and their achievements

No Comments

No Known Activations