INDEX

Explanations

sentences that express emotions and personal reflections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

tracted

-0.16

 Ð½Ð°Ð´Ð°

-0.14

 mote

-0.14

Dyn

-0.13

ptions

-0.13

buscar

-0.13

 mint

-0.12

Nap

-0.12

 accessing

-0.12

 VerfÃ¼gung

-0.12

POSITIVE LOGITS

 hear

0.29

 hears

0.23

 hearing

0.22

 finally

0.21

see

0.21

 Hear

0.20

hear

0.20

 watch

0.20

finally

0.20

 know

0.19

Activations Density 0.085%

sentences that express emotions and personal reflections

No Comments

No Known Activations