INDEX

Explanations

punctuation marks and their contextual usages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Zucker

-0.18

isin

-0.15

arger

-0.15

adera

-0.14

jog

-0.14

oes

-0.14

ÅĤaw

-0.14

isia

-0.13

lava

-0.13

ties

-0.13

POSITIVE LOGITS

ing

0.20

 lawy

0.20

enting

0.19

 advent

0.18

ancing

0.18

ARNING

0.17

ading

0.17

 encrypt

0.16

 strateg

0.16

 strav

0.16

Activations Density 0.205%

punctuation marks and their contextual usages

No Comments

No Known Activations