INDEX

Explanations

references to political and military groups associated with conflict

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

 Journey

-0.15

 journey

-0.15

ìĤ¬ì§Ģ

-0.14

MBOL

-0.14

 journeys

-0.14

 trÃŃ

-0.14

olik

-0.13

 Giang

-0.13

utex

-0.13

_plugins

-0.13

POSITIVE LOGITS

anyahu

0.23

ileaks

0.23

exit

0.22

zbollah

0.19

EXIT

0.17

agate

0.17

xit

0.17

Front

0.16

front

0.16

ebb

0.16

Activations Density 0.304%

references to political and military groups associated with conflict

No Comments

No Known Activations