INDEX

Explanations

terms related to decision-making processes

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

ild

-0.16

orra

-0.15

Gow

-0.15

kke

-0.15

deen

-0.15

usta

-0.14

eldo

-0.14

folk

-0.14

seed

-0.14

iges

-0.14

POSITIVE LOGITS

-making

0.27

naire

0.23

-makers

0.22

 makers

0.21

-maker

0.20

 maker

0.19

al

0.19

 making

0.18

making

0.17

 made

0.17

Activations Density 0.038%

terms related to decision-making processes

No Comments

No Known Activations