INDEX

Explanations

repeated references to the word "the"

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

ensem

-0.16

 inflamm

-0.15

ahoma

-0.15

.AppSettings

-0.14

rzy

-0.14

raÄį

-0.14

Ä±f

-0.14

 ØµÙĨØ¹

-0.14

soles

-0.13

asant

-0.13

POSITIVE LOGITS

 standpoint

0.39

 perspective

0.38

 perspectives

0.28

 Perspective

0.27

 outset

0.27

 depths

0.24

 viewpoint

0.23

 comfort

0.22

pers

0.22

 beginning

0.22

Activations Density 0.101%

repeated references to the word "the"

No Comments

No Known Activations