INDEX

Explanations

special characters and formatting within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

LAP

-0.17

 hipp

-0.15

 Homer

-0.14

odus

-0.14

 Honduras

-0.14

 Lafayette

-0.14

 Appalach

-0.14

alus

-0.14

 Guitar

-0.14

 Huckabee

-0.14

POSITIVE LOGITS

Haz

0.41

Haz

0.36

 Dean

0.33

Dean

0.29

 Energ

0.27

haz

0.26

 dean

0.25

HE

0.25

 Heavenly

0.24

 Hazard

0.23

Activations Density 0.002%

special characters and formatting within the text

No Comments

No Known Activations