INDEX

Explanations

phrases related to applications and applying for various opportunities or licenses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÄŁ

-0.16

IGO

-0.15

eway

-0.15

 Bros

-0.14

uth

-0.14

bat

-0.14

ordan

-0.14

utherland

-0.14

igo

-0.13

POSITIVE LOGITS

 online

0.20

online

0.20

cation

0.17

Online

0.16

 Online

0.16

-online

0.16

é¦

0.15

reet

0.15

ogg

0.15

EDI

0.15

Activations Density 0.028%

phrases related to applications and applying for various opportunities or licenses

No Comments

No Known Activations