INDEX

Explanations

phrases indicating frequency or repetition

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

reesome

-0.16

.scalablytyped

-0.15

alytics

-0.15

áº£i

-0.14

edik

-0.14

Ø§Ø±Ú©

-0.14

æĭĵ

-0.14

dif

-0.14

paged

-0.13

angent

-0.13

POSITIVE LOGITS

 awhile

0.36

 blue

0.30

 while

0.29

blue

0.26

 Blue

0.25

 BLUE

0.24

BLUE

0.23

-blue

0.23

while

0.23

Blue

0.23

Activations Density 0.031%

phrases indicating frequency or repetition

No Comments

No Known Activations