INDEX

Explanations

emotional responses and expressions related to personal feelings

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

regor

-0.18

ALSE

-0.16

-Ð½Ð¸

-0.15

 Flem

-0.15

amespace

-0.15

MOTE

-0.15

oras

-0.14

 discrepan

-0.14

ivement

-0.14

.raises

-0.14

POSITIVE LOGITS

 aware

0.27

 feel

0.23

aware

0.23

 proud

0.21

 uncomfortable

0.20

 Aware

0.19

 comfortable

0.18

sad

0.17

ako

0.17

gig

0.17

Activations Density 0.036%

emotional responses and expressions related to personal feelings

No Comments

No Known Activations