INDEX

Explanations

terms related to imperial and global history

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

nik

-0.17

bjerg

-0.16

apat

-0.16

abouts

-0.16

orgia

-0.15

Ã©nÃ©

-0.15

âĢĮØ¨

-0.15

_blueprint

-0.14

agna

-0.14

POSITIVE LOGITS

wide

0.21

-wide

0.19

/Common

0.17

illis

0.15

istic

0.15

hoff

0.14

éĻħ

0.14

/Foundation

0.14

 wide

0.14

aData

0.14

Activations Density 0.022%

terms related to imperial and global history

No Comments

No Known Activations