INDEX

Explanations

phrases related to organizations and their roles or activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

heimer

-0.16

china

-0.15

isay

-0.15

merce

-0.14

orado

-0.14

Ð¼Ð°Ð·

-0.14

ä¼Ĭ

-0.14

eut

-0.14

achat

-0.14

eyen

-0.14

POSITIVE LOGITS

egend

0.15

ë©´

0.15

ipes

0.14

NZ

0.14

&quot

0.14

 gros

0.14

 inkl

0.13

Ķ

0.13

 Ð²Ð·Ð°Ð¸Ð¼

0.13

NZ

0.13

Activations Density 0.021%

phrases related to organizations and their roles or activities

No Comments

No Known Activations