INDEX

Explanations

mentions of people and interactions in a narrative context

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

 Jewish

-0.18

 Israeli

-0.17

ATUS

-0.16

auer

-0.15

 tang

-0.15

Äįet

-0.15

Israel

-0.15

 Bilim

-0.14

 Israel

-0.14

ModelProperty

-0.14

POSITIVE LOGITS

 Moran

0.22

Mos

0.22

Av

0.22

Guy

0.21

Gil

0.20

Guy

0.20

Av

0.20

Hag

0.19

Adv

0.18

Riv

0.18

Activations Density 0.041%

mentions of people and interactions in a narrative context

No Comments

No Known Activations