INDEX

Explanations

references to the name "Lee."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

st

-0.22

eer

-0.16

most

-0.15

stations

-0.15

opathy

-0.15

\Builder

-0.14

ê¸Ī

-0.14

iÃ©n

-0.14

lyph

-0.14

POSITIVE LOGITS

uw

0.31

ann

0.29

Ann

0.29

ches

0.28

Roy

0.27

za

0.26

Anne

0.26

bron

0.24

ves

0.24

brick

0.24

Activations Density 0.005%

references to the name "Lee."

No Comments

No Known Activations