INDEX

Explanations

terms related to healthcare policies and financial transactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

arella

-0.16

munition

-0.15

apt

-0.14

 tail

-0.14

aju

-0.14

 ç¬

-0.14

 Sunder

-0.13

etta

-0.13

etto

-0.13

ohl

-0.13

POSITIVE LOGITS

 Seal

0.22

0.17

0.16

 seal

0.15

SHIP

0.14

lif

0.14

.portal

0.14

WindowSize

0.14

Ear

0.13

antee

0.13

Activations Density 0.342%

terms related to healthcare policies and financial transactions

No Comments

No Known Activations