INDEX

Explanations

phrases indicating progression or movement through a sequence of events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 bÃ¬

-0.15

ç¯

-0.14

ourg

-0.14

Ã©ric

-0.14

 hindsight

-0.14

Ð½Ð¾Ñĩ

-0.14

uze

-0.13

 Redistributions

-0.13

åŀ

-0.13

 ÏĥÏĦÎ¹

-0.13

POSITIVE LOGITS

 move

0.64

 moving

0.63

 Moving

0.56

 moved

0.55

moving

0.55

 moves

0.54

 Move

0.54

Moving

0.53

move

0.52

Move

0.50

Activations Density 0.167%

phrases indicating progression or movement through a sequence of events

No Comments

No Known Activations