INDEX

Explanations

phrases indicating emotional or subjective states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

we

-0.15

 crossorigin

-0.15

 they

-0.14

HttpException

-0.14

_ipv

-0.13

 someone

-0.13

_processors

-0.13

GLOBALS

-0.13

_depend

-0.13

actories

-0.13

POSITIVE LOGITS

 haber

0.28

que

0.27

 avoir

0.27

 having

0.26

having

0.26

 Having

0.24

Having

0.23

Que

0.21

che

0.20

QUE

0.20

Activations Density 0.030%

phrases indicating emotional or subjective states

No Comments

No Known Activations

phrases indicating emotional or subjective states

No Comments

No Known Activations