INDEX

Explanations

phrases indicating assessment or understanding of various concepts

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

aska

-0.15

iras

-0.15

/Instruction

-0.14

lernen

-0.14

unami

-0.14

vod

-0.13

.bunifuFlatButton

-0.13

.PropTypes

-0.13

iren

-0.13

.MixedReality

-0.13

POSITIVE LOGITS

 idea

0.52

 Idea

0.41

idea

0.40

 picture

0.35

 feel

0.34

 sense

0.32

 notion

0.31

 handle

0.30

 understanding

0.30

 indication

0.29

Activations Density 0.109%

phrases indicating assessment or understanding of various concepts

No Comments

No Known Activations