INDEX

Explanations

programming-related terminology and function definitions

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

lify

-0.18

ishly

-0.18

ary

-0.17

liner

-0.17

ness

-0.16

isan

-0.16

ality

-0.16

EMU

-0.16

arp

-0.16

osate

-0.16

POSITIVE LOGITS

able

0.29

ments

0.28

ings

0.25

ability

0.24

ance

0.22

ables

0.22

ÂŃing

0.21

icut

0.21

ABLE

0.21

mnt

0.20

Activations Density 0.266%

programming-related terminology and function definitions

No Comments

No Known Activations