INDEX

Explanations

programming-related terms and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.33

-0.28

at

-0.27

ar

-0.26

iya

-0.26

iw

-0.24

iy

-0.24

iad

-0.23

er

-0.23

POSITIVE LOGITS

resent

0.23

lication

0.19

resents

0.18

ares

0.18

ooled

0.18

airs

0.18

loid

0.18

lications

0.17

rompt

0.17

ublish

0.17

Activations Density 0.062%

programming-related terms and functions

No Comments

No Known Activations