INDEX

Explanations

mentions of historical events and significant life details related to notable individuals

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

–

-0.23

 whilst

-0.22

 amongst

-0.21

‘

-0.21

 Whilst

-0.19

 towards

-0.18

 neighbouring

-0.18

-0.17

POSITIVE LOGITS

Äįel

0.17

Ã§ok

0.15

 nons

0.15

 nonexistent

0.14

 NONINFRINGEMENT

0.14

à¤¨à¤²

0.14

 buildup

0.14

SError

0.14

usu

0.14

lek

0.14

Activations Density 0.264%

mentions of historical events and significant life details related to notable individuals

No Comments

No Known Activations