INDEX

Explanations

references to religious figures and their historical significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ì§ľ

-0.16

 opat

-0.16

isure

-0.15

Ð·Ñĭ

-0.15

aryawan

-0.15

emente

-0.14

achs

-0.14

illance

-0.14

 ÑĢÐ°Ñħ

-0.14

urat

-0.14

POSITIVE LOGITS

 worship

0.45

 cult

0.40

wor

0.38

 worsh

0.36

 Worship

0.36

 idol

0.35

wor

0.35

 idols

0.31

Wor

0.30

 Idol

0.26

Activations Density 0.189%

references to religious figures and their historical significance

No Comments

No Known Activations