INDEX

Explanations

mathematical terms and concepts, particularly relating to integrals and analytical methods

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

onian

-0.16

quette

-0.15

ãĤµãĤ¤

-0.15

duc

-0.15

upply

-0.14

 nIndex

-0.14

Ð»ÐµÐ¹

-0.14

Vtbl

-0.14

.bridge

-0.14

 ç·

-0.14

POSITIVE LOGITS

 pole

0.42

 poles

0.42

 Pole

0.40

pole

0.38

po

0.28

 erected

0.21

 upright

0.18

 Staff

0.18

 posts

0.18

 erect

0.18

Activations Density 0.062%

mathematical terms and concepts, particularly relating to integrals and analytical methods

No Known Activations