INDEX

Explanations

names of organizations and geographical locations

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

orno

-0.17

ë°į

-0.17

ãĤ¯ãĥĪ

-0.15

INCT

-0.15

rello

-0.15

ÄįnÃŃk

-0.14

 Creek

-0.14

rlen

-0.14

mlin

-0.14

 ÐŁÑĢÐ°

-0.14

POSITIVE LOGITS

 region

0.31

 Region

0.26

 Regional

0.26

-region

0.26

 regional

0.25

region

0.25

 Area

0.21

Region

0.21

(region

0.21

-area

0.20

Activations Density 0.122%

names of organizations and geographical locations

No Comments

No Known Activations