INDEX

Explanations

mentions of nuclear incidents and related regulatory actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

åĿĽ

-0.20

_CID

-0.15

vise

-0.14

 consult

-0.14

 ÑĤÐ¸

-0.14

çª

-0.14

 paving

-0.14

("`

-0.13

ÑĨÐ¸Ðº

-0.13

ÑĤÐ¸Ð½

-0.13

POSITIVE LOGITS

 radiation

0.36

 nuclear

0.36

 Nuclear

0.34

 Fukushima

0.33

 radioactive

0.31

 Radiation

0.31

 Chern

0.29

 reactor

0.29

radi

0.28

 reactors

0.26

Activations Density 0.042%

mentions of nuclear incidents and related regulatory actions

No Comments

No Known Activations