INDEX

Explanations

expressions of gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

åĹ

-0.17

\Plugin

-0.15

gow

-0.14

eck

-0.14

redo

-0.14

essler

-0.14

ansen

-0.14

leans

-0.14

ToDevice

-0.14

èĢĮ

-0.14

POSITIVE LOGITS

for

0.36

for

0.27

for

0.24

 Ð·Ð°

0.23

 whose

0.21

za

0.21

 atas

0.21

à¸ªà¸³à¸«à¸£

0.20

 dafÃ¼r

0.20

 iÃ§in

0.19

Activations Density 0.058%

expressions of gratitude and appreciation

No Comments

No Known Activations