INDEX

Explanations

assertions about the existence or presence of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

incy

-0.16

stav

-0.15

lover

-0.15

quip

-0.15

apos

-0.15

uib

-0.14

adelphia

-0.14

ä¹Łæľī

-0.14

ä¾ĭ

-0.14

ddit

-0.13

POSITIVE LOGITS

 nothing

0.21

 NOTHING

0.18

.neo

0.17

 Nothing

0.17

 nowhere

0.17

 nobody

0.16

 never

0.16

egin

0.15

no

0.15

nothing

0.15

Activations Density 0.085%

assertions about the existence or presence of something

No Comments

No Known Activations