INDEX

Explanations

mentions of boycotts and related actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

#End

-0.16

 Harrison

-0.16

ilden

-0.15

ivan

-0.14

/options

-0.14

kan

-0.14

leases

-0.14

yonel

-0.13

Cul

-0.13

Ore

-0.13

POSITIVE LOGITS

Ø§ÙĪÙĬ

0.18

ress

0.17

ä¹ħ

0.16

aroo

0.16

warn

0.15

orsk

0.15

town

0.15

arro

0.14

oundation

0.14

otron

0.14

Activations Density 0.003%

mentions of boycotts and related actions

No Comments

No Known Activations