INDEX

Explanations

terms related to invasion and conflict scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

irit

-0.17

 Invent

-0.15

ocation

-0.15

hab

-0.15

afia

-0.15

ality

-0.15

ì§ĵ

-0.14

tems

-0.14

enaries

-0.14

enia

-0.14

POSITIVE LOGITS

 invasion

0.24

 Invasion

0.22

 into

0.21

 intrusion

0.20

 invading

0.19

 Into

0.18

 INTO

0.18

prising

0.18

¢åįķ

0.18

 invade

0.17

Activations Density 0.040%

terms related to invasion and conflict scenarios

No Comments

No Known Activations