INDEX

Explanations

phrases that express caution or the need for careful consideration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

rio

-0.15

hari

-0.14

pta

-0.14

áº»

-0.14

iyas

-0.13

ButtonType

-0.13

ptest

-0.13

ismet

-0.13

.effect

-0.12

riority

-0.12

POSITIVE LOGITS

 caveat

0.33

 cave

0.33

 grain

0.32

 Cave

0.31

 grains

0.29

 disclaimer

0.27

 caution

0.27

 qualifiers

0.26

 Grain

0.25

 qualifier

0.24

Activations Density 0.090%

phrases that express caution or the need for careful consideration

No Comments

No Known Activations