INDEX

Explanations

mentions of government departments and agencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oub

-0.14

irt

-0.14

irut

-0.14

uli

-0.14

urt

-0.14

bau

-0.14

pac

-0.14

isz

-0.14

oteca

-0.14

opi

-0.14

POSITIVE LOGITS

 Justice

0.18

 Defense

0.18

Defense

0.17

ilon

0.16

 interior

0.16

 Commerce

0.16

 Interior

0.15

 Homeland

0.15

ardown

0.15

artment

0.15

Activations Density 0.022%

mentions of government departments and agencies

No Comments

No Known Activations