INDEX

Explanations

the word "also" and its variations, indicating a focus on additional information or points being made in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

swers

-0.17

 lidi

-0.15

sti

-0.15

.au

-0.15

lements

-0.15

 sinon

-0.14

ugh

-0.14

swer

-0.14

Ø§Ø±ÙĬØ®

-0.14

ught

-0.14

POSITIVE LOGITS

see

0.22

See

0.22

 note

0.22

 worth

0.21

See

0.20

 included

0.20

 Known

0.19

 Read

0.19

 Included

0.19

included

0.18

Activations Density 0.030%

the word "also" and its variations, indicating a focus on additional information or points being made in the text

No Comments

No Known Activations