INDEX

Explanations

references to quantities or measures of people and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ableOpacity

-0.15

 Certain

-0.15

ile

-0.14

ered

-0.14

 certain

-0.14

thern

-0.14

izik

-0.14

uman

-0.14

uteur

-0.14

fern

-0.13

POSITIVE LOGITS

ãĥ¼ãĥĬ

0.18

ç²Ĵ

0.14

 Duffy

0.14

 POSSIBILITY

0.13

Ð·Ñĥ

0.13

Kob

0.13

obb

0.12

engl

0.12

à¸´à¸¨

0.12

/month

0.12

Activations Density 0.025%

references to quantities or measures of people and events

No Comments

No Known Activations