INDEX

Explanations

sentiments and discussions related to political hypocrisy and societal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ï»¿#

-0.16

ä¸Ģå®ļ

-0.15

ilian

-0.15

ancia

-0.15

uida

-0.15

 STRICT

-0.14

amax

-0.14

 HOWEVER

-0.14

ederland

-0.14

ancias

-0.14

POSITIVE LOGITS

 remotely

0.24

 actually

0.24

 actual

0.23

 basic

0.21

actually

0.20

 inconvenient

0.20

 bothered

0.19

 substance

0.19

any

0.19

 intelligent

0.18

Activations Density 0.357%

sentiments and discussions related to political hypocrisy and societal issues

No Comments

No Known Activations