INDEX

Explanations

terms related to sponsorship and associated licensing processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

erna

-0.16

erne

-0.15

acher

-0.15

ÛĮÚ©ÛĮ

-0.15

fty

-0.15

ty

-0.15

ish

-0.14

-fashioned

-0.14

ERIC

-0.14

POSITIVE LOGITS

ship

0.21

ships

0.20

/support

0.20

aggio

0.19

/prom

0.18

Ļ¨

0.17

ory

0.15

SHIP

0.15

 Morrow

0.15

Activations Density 0.110%

terms related to sponsorship and associated licensing processes

No Comments

No Known Activations