INDEX

Explanations

the first-person singular pronoun "I."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

nie

-0.21

 reck

-0.19

ve

-0.19

na

-0.19

 presum

-0.18

ded

-0.16

fm

-0.16

ena

-0.16

fol

-0.16

eno

-0.16

POSITIVE LOGITS

/flutter

0.18

am

0.18

elts

0.17

/O

0.16

aos

0.16

acob

0.16

 mage

0.16

'm

0.16

Ã³nico

0.16

Ã±

0.15

Activations Density 0.130%

the first-person singular pronoun "I."

No Comments

No Known Activations