INDEX

Explanations

actions related to transportation or movement of people and objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 organ

-0.17

 circ

-0.15

wards

-0.15

lesen

-0.14

 landing

-0.14

ı

-0.14

 Desc

-0.14

argar

-0.14

ward

-0.14

esk

-0.14

POSITIVE LOGITS

 home

0.28

 wherever

0.23

 into

0.22

 along

0.21

 across

0.21

 everywhere

0.21

 sebou

0.19

along

0.19

home

0.18

 Across

0.18

Activations Density 0.115%

actions related to transportation or movement of people and objects

No Comments

No Known Activations