INDEX

Explanations

references to office spaces and furniture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

åľĴ

-0.16

illos

-0.14

Ã´

-0.14

.xz

-0.14

çĶ

-0.14

lint

-0.14

æĶ

-0.14

uchos

-0.14

bed

-0.14

åĪ·

-0.13

POSITIVE LOGITS

 desks

0.35

 office

0.34

 desk

0.34

.office

0.33

 Desk

0.31

office

0.30

desk

0.28

 conference

0.28

-office

0.28

 Office

0.26

Activations Density 0.069%

references to office spaces and furniture

No Comments

No Known Activations