INDEX

Explanations

phrases indicating possession or existence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

essen

-0.16

 Yourself

-0.16

PIC

-0.14

unds

-0.14

acious

-0.14

.lst

-0.14

PIC

-0.14

imar

-0.14

 verw

-0.14

ayas

-0.13

POSITIVE LOGITS

htag

0.23

bara

0.22

htable

0.21

 become

0.21

 implications

0.20

nt

0.20

 always

0.19

 potential

0.19

 consequences

0.19

 roots

0.18

Activations Density 0.133%

phrases indicating possession or existence

No Comments

No Known Activations