INDEX

Explanations

mentions of the Nobel Prize

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

erde

-0.15

yor

-0.15

uner

-0.14

iscard

-0.14

yx

-0.14

 Gill

-0.14

erne

-0.14

vrier

-0.14

usch

-0.14

 Cran

-0.14

POSITIVE LOGITS

 Prize

0.30

 prize

0.28

 Laure

0.22

 laure

0.22

-winning

0.22

 Peace

0.21

 prizes

0.20

 award

0.20

 awarded

0.20

 Nobel

0.20

Activations Density 0.002%

mentions of the Nobel Prize

No Comments

No Known Activations