INDEX

Explanations

references to government surveillance and intelligence operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

iska

-0.17

aira

-0.16

fst

-0.16

atti

-0.15

xFFF

-0.15

opup

-0.14

_digits

-0.14

itest

-0.14

lsen

-0.14

 Oliv

-0.14

POSITIVE LOGITS

 intelligence

0.54

 Intelligence

0.50

intelligence

0.44

 intel

0.36

elligence

0.32

 intelig

0.32

 Intel

0.29

CIA

0.29

Intel

0.26

NSA

0.24

Activations Density 0.084%

references to government surveillance and intelligence operations

No Comments

No Known Activations