INDEX

Explanations

references to systemic corruption in governmental contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

spb

-0.17

nonnull

-0.16

sein

-0.16

XA

-0.15

coop

-0.14

esser

-0.14

ä»®

-0.14

emailer

-0.14

iser

-0.14

EGIN

-0.14

POSITIVE LOGITS

 corruption

0.49

 Corruption

0.46

 corrupt

0.43

èħĲ

0.38

 corrupted

0.36

 graft

0.31

nep

0.31

-cor

0.27

kle

0.26

cron

0.26

Activations Density 0.039%

references to systemic corruption in governmental contexts

No Comments

No Known Activations