INDEX

Explanations

variations of the word "constant."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

uality

-0.17

age

-0.16

ugs

-0.16

erable

-0.15

wan

-0.15

rz

-0.15

azines

-0.15

chod

-0.15

ë§¤

-0.15

íıĲ

-0.15

POSITIVE LOGITS

ellation

0.31

uctor

0.26

antly

0.25

ipation

0.23

ipated

0.21

uctive

0.20

umes

0.20

ancy

0.18

uct

0.18

0.17

Activations Density 0.016%

variations of the word "constant."

No Comments

No Known Activations