INDEX

Explanations

references to online and internet-related content

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yla

-0.15

strup

-0.15

redd

-0.14

esy

-0.14

fu

-0.14

 Fuel

-0.14

fuel

-0.14

.Unicode

-0.13

gr

-0.13

fas

-0.13

POSITIVE LOGITS

ema

0.15

Ã¡vka

0.15

/Web

0.14

Ø³Ø¨

0.14

usu

0.14

ibar

0.14

/App

0.14

igu

0.13

 dealloc

0.13

/email

0.13

Activations Density 0.393%

references to online and internet-related content

No Comments

No Known Activations