INDEX

Explanations

negative or conditional phrases regarding existence or state of being

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

wd

-0.16

XE

-0.14

LAY

-0.14

urum

-0.14

xEB

-0.14

uyáº¿t

-0.14

abei

-0.14

cano

-0.13

openhagen

-0.13

jon

-0.13

POSITIVE LOGITS

 true

0.35

 happening

0.31

 done

0.29

true

0.29

 True

0.26

True

0.26

 happens

0.26

 happen

0.26

 TRUE

0.25

done

0.25

Activations Density 0.120%

negative or conditional phrases regarding existence or state of being

No Comments

No Known Activations