INDEX

Explanations

mentions of political controversies or allegations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

UTO

-0.17

 UNION

-0.15

UDA

-0.15

ffen

-0.15

anye

-0.14

arket

-0.14

uto

-0.13

 SWITCH

-0.13

mailto

-0.13

utf

-0.13

POSITIVE LOGITS

 intelligence

0.40

 Intelligence

0.35

intelligence

0.32

CIA

0.32

 Pentagon

0.30

 State

0.29

 Defense

0.28

 intel

0.27

 administration

0.26

 White

0.26

Activations Density 0.183%

mentions of political controversies or allegations

No Comments

No Known Activations