INDEX

Explanations

references to time durations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

unt

-0.17

erez

-0.16

upon

-0.15

for

-0.15

 upon

-0.15

UNT

-0.15

 later

-0.14

apon

-0.14

ucci

-0.14

resh

-0.14

POSITIVE LOGITS

 leading

0.31

 Leading

0.25

leading

0.25

Leading

0.24

 directly

0.23

 immediately

0.21

 following

0.20

 immedi

0.19

 takip

0.18

following

0.17

Activations Density 0.033%

references to time durations

No Comments

No Known Activations