INDEX

Explanations

phrases indicating the act of examining or reviewing something closely

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Appearance

-0.25

Appearance

-0.24

 appearance

-0.23

 appearances

-0.22

appearance

-0.22

 appearing

-0.20

 Appears

-0.20

 appears

-0.20

 appeared

-0.19

appear

-0.19

POSITIVE LOGITS

 look

0.67

look

0.56

 Look

0.53

Look

0.49

 LOOK

0.48

_look

0.47

 looks

0.45

.look

0.45

 looked

0.42

 looking

0.40

Activations Density 0.051%

phrases indicating the act of examining or reviewing something closely

No Comments

No Known Activations