INDEX

Explanations

punctuation marks throughout 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 @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

elts

-0.15

inta

-0.14

celed

-0.14

anos

-0.14

haf

-0.14

 result

-0.14

ãĤ«ãĥ«

-0.13

Reviewed

-0.13

SKU

-0.13

 sometimes

-0.13

POSITIVE LOGITS

 according

0.29

 According

0.24

According

0.24

according

0.23

 exact

0.22

Exact

0.21

 Exact

0.20

exact

0.20

 details

0.19

 Expect

0.19

Activations Density 0.062%

punctuation marks throughout the text

No Comments

No Known Activations