INDEX

Explanations

references to subtle suggestions or hints in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Ø¨Ø§Ø±

-0.18

iser

-0.16

 Angeles

-0.15

ÙĤÙħ

-0.15

olly

-0.15

arde

-0.15

ãģĤãģĴ

-0.14

/install

-0.14

exels

-0.14

bar

-0.14

POSITIVE LOGITS

 hint

0.23

 towards

0.21

 toward

0.21

blick

0.20

lessly

0.20

 hints

0.19

utherland

0.18

hint

0.18

Trou

0.17

 clue

0.17

Activations Density 0.021%

references to subtle suggestions or hints in the text

No Comments

No Known Activations