INDEX

Explanations

keywords and phrases related to insurance policies and financial terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

erte

-0.15

 branches

-0.15

 Orig

-0.15

branches

-0.15

vent

-0.15

illy

-0.14

ILLE

-0.14

elu

-0.14

bler

-0.14

Branch

-0.14

POSITIVE LOGITS

º

0.18

-alist

0.17

anean

0.17

itto

0.16

iag

0.15

isti

0.15

ensburg

0.14

ghi

0.14

agna

0.14

etsk

0.14

Activations Density 0.065%

keywords and phrases related to insurance policies and financial terminology

No Comments

No Known Activations