INDEX

Explanations

states of being and emotional conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Ø§ÙĦØ¥

-0.19

gom

-0.15

editable

-0.15

chet

-0.15

pite

-0.15

 desperation

-0.14

isser

-0.14

otec

-0.14

 Catalog

-0.14

 loneliness

-0.14

POSITIVE LOGITS

ret

0.33

 adverse

0.29

 sque

0.24

 uncomfortable

0.24

 resistant

0.23

 appreh

0.23

le

0.22

 disin

0.22

-resistant

0.21

amb

0.21

Activations Density 0.164%

states of being and emotional conditions

No Comments

No Known Activations