INDEX

Explanations

instances of the word "the" and variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 possibility

-0.16

ffects

-0.14

burg

-0.14

ovic

-0.14

-0.13

 slightest

-0.13

 whereabouts

-0.13

å®Ŀ

-0.13

OrNil

-0.13

verture

-0.13

POSITIVE LOGITS

 thing

0.41

 reason

0.38

 problem

0.33

 interesting

0.30

 funny

0.29

 trick

0.29

 Thing

0.29

 trouble

0.29

 beauty

0.29

key

0.27

Activations Density 0.343%

instances of the word "the" and variations of it

No Comments

No Known Activations