INDEX

Explanations

references to specific locations, particularly cities and regions

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

.poster

-0.15

uzz

-0.15

ä¼ı

-0.14

å¹¹ç·ļ

-0.14

abus

-0.14

 Zones

-0.14

yect

-0.14

-0.13

ì¡´

-0.13

utt

-0.13

POSITIVE LOGITS

 area

0.31

 greater

0.30

 region

0.30

greater

0.27

tri

0.27

area

0.27

Tri

0.24

.area

0.23

region

0.21

 surrounding

0.20

Activations Density 0.165%

references to specific locations, particularly cities and regions

No Comments

No Known Activations