INDEX

Explanations

phrases related to services, documentation, and requirements for events or programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

/Typography

-0.19

ads

-0.15

icket

-0.15

odos

-0.15

ufe

-0.15

IMIZE

-0.15

ickets

-0.14

 dipl

-0.14

ught

-0.14

 bids

-0.14

POSITIVE LOGITS

 copy

0.26

 link

0.23

copy

0.19

 Copy

0.18

Copy

0.17

 written

0.17

 list

0.17

 hyperlink

0.17

 COPY

0.17

link

0.16

Activations Density 0.238%

phrases related to services, documentation, and requirements for events or programs

No Comments

No Known Activations