INDEX

Explanations

phrases related to academic or professional achievements and challenges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Alright

-0.31

 towards

-0.27

 judgement

-0.27

 amongst

-0.27

 alright

-0.27

 whilst

-0.27

 Alright

-0.25

owards

-0.25

 Towards

-0.24

‘

-0.23

POSITIVE LOGITS

 Dumpster

0.28

Web

0.25

 nonexistent

0.24

 nons

0.22

 nonatomic

0.21

 nonzero

0.20

 Webcam

0.20

 prere

0.19

 multis

0.18

 multit

0.18

Activations Density 1.069%

phrases related to academic or professional achievements and challenges

No Comments

No Known Activations