INDEX

Explanations

references to boundaries or limits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

rish

-0.16

ownik

-0.16

rone

-0.16

awns

-0.15

Ø¬Ø§ÙĨ

-0.14

tod

-0.14

erm

-0.14

ataires

-0.14

Ã¼ss

-0.14

ableView

-0.14

POSITIVE LOGITS

 bounds

0.39

 confines

0.38

 framework

0.33

 boundaries

0.32

 frame

0.28

 scope

0.27

framework

0.27

 ambit

0.27

 limits

0.27

 walls

0.26

Activations Density 0.149%

references to boundaries or limits

No Comments

No Known Activations