INDEX

Explanations

references to collective structures or entities, such as groups or teams

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

avail

-0.19

ä¸ĢåĪĩ

-0.16

engu

-0.15

Ã¤nge

-0.15

onden

-0.14

å§ĭ

-0.14

Ð¾Ð´Ð°Ð²

-0.14

aily

-0.14

elper

-0.14

POSITIVE LOGITS

 unique

0.24

 respective

0.23

çĭ¬ç«ĭ

0.23

 separately

0.23

 respectively

0.21

 distinct

0.20

unique

0.20

çį¨

0.20

.unique

0.20

 independently

0.19

Activations Density 0.176%

references to collective structures or entities, such as groups or teams

No Comments

No Known Activations