INDEX

Explanations

terms related to education and occupational qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

asil

-0.17

bes

-0.16

uth

-0.15

 Manifest

-0.15

ugin

-0.15

 proven

-0.15

ava

-0.14

Rut

-0.14

abad

-0.14

POSITIVE LOGITS

ValueCollection

0.20

.scalablytyped

0.19

 ******************************************************************************/↵

0.17

.ogg

0.17

èĽ

0.16

istrov

0.16

.AF

0.16

alous

0.15

CRET

0.15

RIPTION

0.15

Activations Density 0.245%

terms related to education and occupational qualifications

No Comments

No Known Activations