INDEX

Explanations

questions that begin with "how."

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

oter

-0.13

_UNDEF

-0.13

OTAL

-0.13

incr

-0.13

 trÃŃ

-0.12

mins

-0.12

imedia

-0.12

 overposting

-0.12

ãģĽãģ¦

-0.12

 brilliance

-0.12

POSITIVE LOGITS

do

0.39

 does

0.34

did

0.32

are

0.30

 should

0.30

can

0.30

 would

0.29

 might

0.28

 have

0.28

 will

0.27

Activations Density 0.039%

questions that begin with "how."

No Comments

No Known Activations