INDEX

Explanations

references to financial years and fiscal data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ergus

-0.17

 what

-0.16

IDD

-0.14

chez

-0.14

illin

-0.14

 vigilant

-0.14

olec

-0.14

Ctrls

-0.14

ehen

-0.14

 recip

-0.14

POSITIVE LOGITS

 COVID

0.29

COVID

0.27

 Covid

0.24

 covid

0.24

 Coronavirus

0.23

 coronavirus

0.21

0.19

 pandemic

0.19

 Kavanaugh

0.18

 androidx

0.17

Activations Density 0.465%

references to financial years and fiscal data

No Comments

No Known Activations