INDEX

Explanations

references to religious texts and teachings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Jesus

-0.18

Jesus

-0.18

å¥½äºĨ

-0.15

ALLE

-0.15

Ø³ÙĦ

-0.15

Î¸Î·

-0.15

 Coun

-0.15

shint

-0.14

.prot

-0.14

 Luther

-0.14

POSITIVE LOGITS

etz

0.16

 Cohen

0.16

ertz

0.15

shl

0.15

Lev

0.15

iyim

0.15

ignon

0.15

rimon

0.14

Av

0.14

COPE

0.14

Activations Density 0.183%

references to religious texts and teachings

No Comments

No Known Activations

references to religious texts and teachings

No Comments

No Known Activations