INDEX

Explanations

occurrences of specific locations and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

branches

-0.16

Overrides

-0.14

est

-0.14

_FLAGS

-0.14

PropertyDescriptor

-0.14

amen

-0.13

_override

-0.13

ëŀĮ

-0.13

iii

-0.13

åŁİå¸Ĥ

-0.13

POSITIVE LOGITS

 Institution

0.22

 Hospital

0.21

 Museum

0.21

 Brewery

0.21

 School

0.20

 Stadium

0.20

 Pradesh

0.20

 College

0.19

 Observatory

0.19

 Airport

0.18

Activations Density 0.354%

occurrences of specific locations and institutions

No Comments

No Known Activations