INDEX

Explanations

references to government surveillance and intelligence activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

uv

-0.16

rag

-0.15

_clone

-0.15

Ã¥

-0.14

.auto

-0.14

itness

-0.14

.Mock

-0.13

 plagiar

-0.13

è°ĥ

-0.13

 springfox

-0.13

POSITIVE LOGITS

 warrant

0.25

 Bulk

0.25

NSA

0.24

 surveillance

0.23

Bulk

0.23

 Surveillance

0.22

 Prism

0.21

 bulk

0.21

 Wire

0.20

bulk

0.20

Activations Density 0.038%

references to government surveillance and intelligence activities

No Comments

No Known Activations