INDEX

Explanations

terms related to religious orders and specific religious identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

edit

-0.16

lass

-0.16

ular

-0.15

iteur

-0.15

 programm

-0.15

CRT

-0.14

Sp

-0.14

for

-0.14

çķ

-0.14

POSITIVE LOGITS

aghetti

0.18

chine

0.17

irie

0.16

 HÃ¼s

0.16

paces

0.15

antics

0.15

vla

0.15

esco

0.15

 TextAlign

0.15

unnable

0.15

Activations Density 0.003%

terms related to religious orders and specific religious identifiers

No Comments

No Known Activations