INDEX

Explanations

references to the word "die" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

zier

-0.15

ä¿ºãģ¯

-0.15

ifetime

-0.15

urations

-0.15

OLER

-0.15

alley

-0.15

.checkNotNull

-0.15

ngine

-0.14

çĽ´æĴŃ

-0.14

plain

-0.14

POSITIVE LOGITS

hard

0.35

lectric

0.33

-hard

0.32

ffen

0.27

go

0.25

Hard

0.24

LECT

0.24

bold

0.23

cast

0.23

lect

0.23

Activations Density 0.008%

references to the word "die" in various contexts

No Comments

No Known Activations