INDEX

Explanations

occurrences of the prefix "pre."

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

sWith

-0.24

-0.23

sy

-0.22

sch

-0.22

-0.21

sal

-0.21

sj

-0.20

sin

-0.20

è§Ī

-0.20

POSITIVE LOGITS

ponder

0.28

lude

0.27

cludes

0.25

achers

0.24

ceed

0.24

face

0.24

cepts

0.24

zzo

0.24

clude

0.24

cession

0.24

Activations Density 0.013%

occurrences of the prefix "pre."

No Comments

No Known Activations