INDEX

Explanations

terms related to online privacy and data collection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ugu

-0.15

 slik

-0.15

 skew

-0.15

Stub

-0.15

alar

-0.14

reate

-0.14

/swagger

-0.14

venes

-0.14

.Span

-0.14

.trailing

-0.14

POSITIVE LOGITS

 soils

0.33

SO

0.33

SO

0.33

ãĤ½

0.32

-so

0.31

soc

0.28

_so

0.28

 Soil

0.28

eso

0.27

_SO

0.27

Activations Density 0.051%

terms related to online privacy and data collection

No Comments

No Known Activations