INDEX

Explanations

titles of historical or fictional works, particularly focusing on ships or vessels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ãĥ¼ãĥª

-0.15

 Army

-0.14

aggi

-0.14

Caj

-0.14

veh

-0.14

cen

-0.14

veh

-0.14

ï¼ľ

-0.14

 Sergeant

-0.14

 Springs

-0.14

POSITIVE LOGITS

 flagship

0.18

VOC

0.18

loops

0.18

 Nelson

0.17

 blockade

0.16

gun

0.16

vore

0.16

ulture

0.15

 Pendant

0.15

 Corvette

0.15

Activations Density 0.023%

titles of historical or fictional works, particularly focusing on ships or vessels

No Comments

No Known Activations