INDEX

Explanations

references to various U.S. presidents and their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ÑĢ

-0.14

ig

-0.14

paralleled

-0.14

dÃŃ

-0.14

ved

-0.14

 Tick

-0.14

ÄĽj

-0.13

å¿

-0.13

ously

-0.13

ouver

-0.13

POSITIVE LOGITS

addock

0.16

izont

0.15

/state

0.15

annes

0.14

rams

0.14

istrovstvÃŃ

0.13

/community

0.13

errupt

0.13

ìĭ¤

0.13

args

0.13

Activations Density 0.035%

references to various U.S. presidents and their actions

No Comments

No Known Activations