INDEX

Explanations

variations of the word "syndicate."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

cas

-0.16

ledged

-0.16

lbrace

-0.16

-0.15

er

-0.15

 arch

-0.15

itre

-0.14

ATEGORIES

-0.14

odor

-0.14

POSITIVE LOGITS

icate

0.32

icated

0.31

icates

0.25

ication

0.24

rome

0.22

posium

0.22

 synd

0.21

 Synd

0.20

ICATION

0.19

icator

0.19

Activations Density 0.004%

variations of the word "syndicate."

No Comments

No Known Activations