INDEX

Explanations

references to historical or political contexts related to Israel and Palestine

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

oun

-0.17

 deriv

-0.17

 hemorrh

-0.16

iquÃ©

-0.15

 weren

-0.15

 Visit

-0.14

iquer

-0.14

 Mock

-0.14

 pund

-0.14

 proven

-0.14

POSITIVE LOGITS

 tire

0.21

 attire

0.20

 lance

0.20

pose

0.19

agit

0.19

teste

0.19

ifie

0.19

 relie

0.18

 filme

0.18

 fait

0.18

Activations Density 0.023%

references to historical or political contexts related to Israel and Palestine

No Comments

No Known Activations