INDEX

Explanations

expressions of gratitude and thankfulness

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

ince

-0.19

VICES

-0.15

Î¯Î¿

-0.14

leston

-0.14

ifa

-0.14

oir

-0.14

ihan

-0.14

oplan

-0.13

 themselves

-0.13

apr

-0.13

POSITIVE LOGITS

 very

0.34

 again

0.32

 much

0.24

very

0.24

so

0.23

 once

0.23

again

0.23

 kindly

0.23

 VERY

0.23

 ever

0.22

Activations Density 0.033%

expressions of gratitude and thankfulness

No Comments

No Known Activations