INDEX

Explanations

expressions of gratitude and thanks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

alth

-0.17

tring

-0.16

sko

-0.16

kaar

-0.16

vig

-0.15

ein

-0.15

orro

-0.15

ugi

-0.15

imbus

-0.14

tlement

-0.14

POSITIVE LOGITS

sgiving

0.27

ably

0.16

fully

0.16

ram

0.16

ÛĮÙĩ

0.16

able

0.16

 Winn

0.15

atory

0.14

nowled

0.14

ru

0.14

Activations Density 0.042%

expressions of gratitude and thanks

No Comments

No Known Activations