INDEX

Explanations

references to teaching, learning, and various game mechanics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-0.14

QUAL

-0.13

 lÃ´

-0.13

odynam

-0.13

ked

-0.13

ovna

-0.13

era

-0.13

 ÑģÐ°Ð¼Ðµ

-0.13

ÙİÙī

-0.13

POSITIVE LOGITS

 phenomenon

0.18

 approach

0.18

 adlÄ±

0.17

çļĦæĥħåĨµ

0.17

 kind

0.16

zzle

0.15

çļĦéĹ®é¢ĺ

0.15

ìĿ´ëĿ¼ëĬĶ

0.15

 tÃŃ

0.15

 scenario

0.15

Activations Density 0.485%

references to teaching, learning, and various game mechanics

No Comments

No Known Activations

references to teaching, learning, and various game mechanics

No Comments

No Known Activations