INDEX

Explanations

keywords related to modifications or changes in context

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

est

-0.41

er

-0.36

th

-0.35

apult

-0.31

itud

-0.29

ar

-0.28

Item

-0.27

Of

-0.24

eru

-0.23

erator

-0.23

POSITIVE LOGITS

0.18

 unsub

0.17

ÛĮÙģ

0.16

ght

0.16

uset

0.15

ties

0.15

tir

0.15

tains

0.15

tÃŃ

0.15

tal

0.15

Activations Density 0.054%

keywords related to modifications or changes in context

No Comments

No Known Activations