INDEX

Explanations

references to refugee and detention contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

QUIT

-0.16

LINK

-0.15

herits

-0.14

 cabinets

-0.14

ouz

-0.14

åº«

-0.14

agog

-0.14

ecta

-0.14

 Cabinets

-0.14

Inspectable

-0.13

POSITIVE LOGITS

 camp

0.49

 camps

0.46

 Camp

0.39

 tent

0.35

camp

0.34

Camp

0.34

enc

0.34

tent

0.28

 tents

0.28

 Tent

0.27

Activations Density 0.042%

references to refugee and detention contexts

No Comments

No Known Activations