INDEX

Explanations

terms related to cybersecurity and government contracts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

æĬľ

-0.15

raya

-0.15

ruitment

-0.15

åľĺ

-0.14

anson

-0.14

ç«¶

-0.14

asons

-0.14

.$.

-0.14

oka

-0.14

Monitoring

-0.13

POSITIVE LOGITS

 sustain

0.28

 depot

0.23

 mater

0.22

mun

0.21

 Depot

0.21

 acquisition

0.20

Do

0.20

 Acquisition

0.19

 doctr

0.18

/Base

0.18

Activations Density 0.053%

terms related to cybersecurity and government contracts

No Comments

No Known Activations