INDEX

Explanations

adverbs and adjectives that have political, cultural, or social implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ORB

-0.15

ables

-0.15

able

-0.15

 Voll

-0.14

erez

-0.14

ive

-0.14

fak

-0.14

à¤¤à¤®

-0.14

ario

-0.14

elle

-0.14

POSITIVE LOGITS

 speaking

0.25

 sound

0.24

sound

0.24

 minded

0.22

 Speaking

0.21

-speaking

0.20

Sound

0.20

 SOUND

0.20

/math

0.19

 Sound

0.19

Activations Density 0.039%

adverbs and adjectives that have political, cultural, or social implications

No Comments

No Known Activations