INDEX

Explanations

programming-related elements and operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 dedicated

-0.20

 Dedicated

-0.19

ä»¥åĲİ

-0.19

 invented

-0.18

licensed

-0.17

 dedicate

-0.16

 licensed

-0.16

 necessity

-0.16

 request

-0.16

icensed

-0.15

POSITIVE LOGITS

 reached

0.41

 reaching

0.36

 faced

0.35

 reachable

0.33

 reaches

0.33

 facing

0.33

 touched

0.31

 reach

0.29

 overcome

0.28

 seen

0.28

Activations Density 0.104%

programming-related elements and operations

No Comments

No Known Activations