INDEX

Explanations

phrases related to divine authority and religious instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ModelProperty

-0.19

ourg

-0.17

orca

-0.16

bourg

-0.16

pte

-0.16

 Incontri

-0.15

egin

-0.15

ï¼©

-0.15

zew

-0.15

uth

-0.15

POSITIVE LOGITS

0.24

Oh

0.22

Ver

0.19

Beh

0.19

ver

0.19

 therefore

0.19

oh

0.18

 amen

0.18

 Therefore

0.18

let

0.18

Activations Density 0.289%

phrases related to divine authority and religious instructions

No Comments

No Known Activations