INDEX

Explanations

terms related to military escalation and conflict situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

IBE

-0.17

cade

-0.15

ayer

-0.15

 bottoms

-0.15

 Mall

-0.15

-0.14

GIN

-0.14

gers

-0.14

yles

-0.14

POSITIVE LOGITS

tran

0.16

Ã¡Å¡

0.16

)./

0.14

ÏĦÎ¹Ïĥ

0.14

ucher

0.14

ngu

0.14

onu

0.14

ikut

0.13

fef

0.13

 Credits

0.13

Activations Density 0.066%

terms related to military escalation and conflict situations

No Comments

No Known Activations