INDEX

Explanations

terms related to corruption and financial misconduct

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

.scalablytyped

-0.20

GuidId

-0.17

actionDate

-0.16

ÑĤÐ°Ð±

-0.16

/stdc

-0.15

Î»Î¹Î¿

-0.15

##_

-0.15

.Microsoft

-0.14

ushman

-0.14

/INFO

-0.14

POSITIVE LOGITS

 fraud

0.18

phant

0.17

ä¸²

0.17

 ghost

0.16

 phantom

0.16

ks

0.16

0.15

 records

0.15

 fake

0.15

bil

0.15

Activations Density 0.169%

terms related to corruption and financial misconduct

No Comments

No Known Activations