INDEX

Explanations

references to World War II and its related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.22

-0.16

unt

-0.15

quer

-0.15

ould

-0.15

ster

-0.15

Cav

-0.15

wich

-0.14

ong

-0.14

mg

-0.14

POSITIVE LOGITS

Ã³ln

0.17

ëĳ¥

0.16

iyel

0.16

panic

0.15

ÃĴ

0.15

NECT

0.14

/Gate

0.14

ermalink

0.14

nehmer

0.14

clidean

0.14

Activations Density 0.010%

references to World War II and its related contexts

No Comments

No Known Activations