INDEX

Explanations

instances of 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 @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

-0.14

rzy

-0.14

asant

-0.14

raÄį

-0.14

Ã¼st

-0.14

meden

-0.14

ieber

-0.14

abant

-0.13

ItemAt

-0.13

ienda

-0.13

POSITIVE LOGITS

 standpoint

0.45

 perspective

0.43

 perspectives

0.32

 Perspective

0.31

 outset

0.30

 viewpoint

0.28

 depths

0.26

 Perspectives

0.25

 beginning

0.24

pers

0.24

Activations Density 0.092%

instances of the word "the."

No Comments

No Known Activations