INDEX

Explanations

expressions of happiness and related positive emotions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

evin

-0.16

werk

-0.16

rag

-0.15

ile

-0.14

veloper

-0.14

ching

-0.14

Ð¾Ð³ÑĢÐ°Ð´

-0.14

acles

-0.14

à¸¸à¸Ľ

-0.14

POSITIVE LOGITS

-go

0.19

arters

0.16

MeasureSpec

0.15

faker

0.15

avier

0.15

happy

0.15

oi

0.14

imir

0.14

isten

0.14

ione

0.14

Activations Density 0.033%

expressions of happiness and related positive emotions

No Comments

No Known Activations