INDEX

Explanations

terms related to the insurance and financial industries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

cheiden

-0.16

oda

-0.16

aben

-0.15

/Branch

-0.15

inan

-0.15

incare

-0.14

 Freund

-0.14

 Governance

-0.14

pras

-0.14

rophe

-0.13

POSITIVE LOGITS

 industry

0.26

 sector

0.24

sector

0.20

 Industry

0.19

industry

0.18

 sectors

0.17

-sector

0.17

-grade

0.16

Industry

0.16

Sector

0.16

Activations Density 0.139%

terms related to the insurance and financial industries

No Comments

No Known Activations