INDEX

Explanations

terms related to health effects and research findings on potential risks and benefits

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

AZE

-0.18

.scalablytyped

-0.17

arias

-0.16

Ð¾Ð´Ð°ÑĢ

-0.15

ldkf

-0.15

elho

-0.15

hread

-0.14

><![

-0.14

ernal

-0.14

vironment

-0.14

POSITIVE LOGITS

SD

0.15

å¡ļ

0.15

Toy

0.14

¤íĶĦ

0.14

ney

0.13

inas

0.13

ÏĦÎµÎ¹

0.13

erra

0.13

isset

0.13

ana

0.13

Activations Density 0.409%

terms related to health effects and research findings on potential risks and benefits

No Comments

No Known Activations