INDEX

Explanations

references to specific events and categories in news articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

abox

-0.19

ullan

-0.17

eft

-0.15

ibox

-0.14

 Verg

-0.14

loh

-0.14

 Stef

-0.13

/generated

-0.13

beros

-0.13

abet

-0.13

POSITIVE LOGITS

DMI

0.16

 Fountain

0.15

ACS

0.14

Sm

0.14

 hiatus

0.14

orsi

0.14

Åº

0.14

ifestyles

0.14

 Anthem

0.14

RIORITY

0.13

Activations Density 0.358%

references to specific events and categories in news articles

No Comments

No Known Activations