INDEX

Explanations

phrases emphasizing validation or emphasis on points made in a discussion

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

 bÃ¥de

-0.16

xies

-0.15

antine

-0.15

ãĥªãĤ¢

-0.15

ansk

-0.14

ago

-0.14

ront

-0.14

çĶļèĩ³

-0.14

xbc

-0.14

áº£

-0.14

POSITIVE LOGITS

 though

0.28

 when

0.21

Though

0.21

 those

0.20

when

0.19

though

0.19

if

0.19

-handed

0.19

 within

0.18

 worse

0.18

Activations Density 0.029%

phrases emphasizing validation or emphasis on points made in a discussion

No Comments

No Known Activations