INDEX

Explanations

negative emotions and experiences related to regret or loss

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ily

-0.18

ered

-0.18

-0.17

iesel

-0.16

eenth

-0.16

edImage

-0.16

ender

-0.16

ceae

-0.16

IZED

-0.16

ings

-0.16

POSITIVE LOGITS

ting

0.71

ging

0.47

TING

0.45

ted

0.43

table

0.36

ters

0.36

tings

0.34

ter

0.32

bing

0.31

GING

0.30

Activations Density 0.054%

negative emotions and experiences related to regret or loss

No Comments

No Known Activations