INDEX

Explanations

significant events or milestones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 parking

-0.17

 Parking

-0.16

elsen

-0.16

Parking

-0.15

 traffic

-0.15

äº¤éĢļ

-0.15

isky

-0.14

kud

-0.14

ä»ĭ

-0.14

estre

-0.14

POSITIVE LOGITS

 onboard

0.75

 aboard

0.65

board

0.52

 board

0.50

-board

0.46

 Board

0.43

Board

0.42

 boarding

0.41

 passengers

0.41

 bord

0.41

Activations Density 0.204%

significant events or milestones

No Comments

No Known Activations