INDEX

Explanations

references to Jewish history and its portrayal in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

STA

-0.15

 NATO

-0.15

IDS

-0.14

TI

-0.14

Ø¬Ø§ÙĨ

-0.14

Nep

-0.14

 Giang

-0.14

ìĦ¼

-0.14

ery

-0.13

Ã¤Ã¤

-0.13

POSITIVE LOGITS

 Mandatory

0.34

 Mand

0.29

 Palestine

0.28

 Partition

0.25

Pale

0.24

MAND

0.24

 mand

0.24

 mandate

0.24

mand

0.23

 Zionist

0.22

Activations Density 0.033%

references to Jewish history and its portrayal in narratives

No Comments

No Known Activations