INDEX

Explanations

numerical values, particularly those related to measurements or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

oader

-0.17

kil

-0.15

.Usage

-0.15

craft

-0.15

fillType

-0.14

ÙĪØ±ÛĮ

-0.14

.nd

-0.14

unday

-0.14

 xuyÃªn

-0.13

abilia

-0.13

POSITIVE LOGITS

gether

0.25

/from

0.21

plevel

0.20

tem

0.17

pline

0.17

tems

0.17

asting

0.16

icina

0.16

ledo

0.15

mm

0.15

Activations Density 1.645%

numerical values, particularly those related to measurements or quantities

No Comments

No Known Activations