INDEX

Explanations

relationships and comparisons in various contexts

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

afil

-0.16

åĳĬ

-0.15

ovel

-0.14

ismet

-0.14

aze

-0.14

 alot

-0.13

}->{

-0.13

ä¸į

-0.13

 BoxFit

-0.13

POSITIVE LOGITS

 ÙĥÙħØ§

0.26

 like

0.23

as

0.22

åĥı

0.22

 tolik

0.21

 same

0.20

íģ¼

0.20

éĤ£æł·

0.19

ãģ»ãģ©

0.19

ãģ®ãĤĪãģĨãģ«

0.19

Activations Density 0.286%

relationships and comparisons in various contexts

No Comments

No Known Activations