INDEX

Explanations

words related to spiritual or religious concepts and figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

urette

-0.17

rosso

-0.16

ãģ¡ãĤī

-0.16

lotte

-0.16

umph

-0.14

angkan

-0.14

Ã¤llt

-0.14

hari

-0.14

<*

-0.14

.dsl

-0.14

POSITIVE LOGITS

 Pyramid

0.17

ãĤ¥

0.15

ank

0.14

 pyramid

0.14

Sol

0.14

.py

0.14

oub

0.14

æĸ

0.14

 fort

0.14

Zwe

0.13

Activations Density 0.059%

words related to spiritual or religious concepts and figures

No Comments

No Known Activations