INDEX

Explanations

elements related to shopping locations and activities

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

 helicopt

-0.15

 reservoir

-0.14

Ã¼ndeki

-0.14

/set

-0.14

 cottage

-0.14

 latency

-0.14

 intr

-0.14

Ĺi

-0.13

 camps

-0.13

 bunk

-0.13

POSITIVE LOGITS

 mall

0.49

 shopping

0.48

 Shopping

0.44

 malls

0.43

 Mall

0.43

-shopping

0.40

shopping

0.38

Shopping

0.37

mall

0.36

 shoppers

0.35

Activations Density 0.236%

elements related to shopping locations and activities

No Comments

No Known Activations