INDEX

Explanations

elements related to formatting and style in texts, particularly bold and italics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

rary

-0.17

ession

-0.15

elez

-0.15

ehir

-0.15

usk

-0.14

onomous

-0.14

aniel

-0.14

.lu

-0.14

igue

-0.14

enberg

-0.14

POSITIVE LOGITS

 bold

0.33

italic

0.30

 Bold

0.29

bold

0.29

 italic

0.28

Italic

0.28

 Ital

0.27

-bold

0.26

Bold

0.26

 underline

0.25

Activations Density 0.048%

elements related to formatting and style in texts, particularly bold and italics

No Comments

No Known Activations