INDEX

Explanations

variations of the word "rag" and its derivatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

",-

-0.15

akest

-0.15

 Burgess

-0.14

åħĭ

-0.14

 aktual

-0.14

 Ø´ÙĨØ§Ø³ÛĮ

-0.14

 Budd

-0.13

eel

-0.13

fluence

-0.13

aft

-0.13

POSITIVE LOGITS

ged

0.31

doll

0.22

ardless

0.19

weed

0.19

time

0.18

ging

0.17

ocking

0.16

istration

0.16

ieÅ¼

0.16

Activations Density 0.003%

variations of the word "rag" and its derivatives

No Comments

No Known Activations