INDEX

Explanations

phrases related to policies or initiatives that are implemented on a broad geographic scale

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

affe

-0.17

ibus

-0.14

oad

-0.14

urs

-0.14

IBE

-0.14

lin

-0.14

AFE

-0.14

¢

-0.13

orte

-0.13

ortic

-0.13

POSITIVE LOGITS

Ã¡nu

0.16

/month

0.15

ISOString

0.15

ento

0.15

 ÐºÐ°Ñģ

0.15

enger

0.14

Ä±f

0.14

oug

0.14

imbledon

0.14

enticator

0.14

Activations Density 0.008%

phrases related to policies or initiatives that are implemented on a broad geographic scale

No Comments

No Known Activations