INDEX

Explanations

phrases indicating origins or beginnings

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jÃŃt

-0.16

.MixedReality

-0.15

ewis

-0.15

ÑĢÐ¾Ð³

-0.14

Ð¾Ð³Ð¾Ð´

-0.14

jer

-0.14

 Clipboard

-0.14

 newArr

-0.14

.scalablytyped

-0.14

éĸ

-0.14

POSITIVE LOGITS

 beginning

0.37

 dÃ¨s

0.37

 earliest

0.35

 early

0.32

 since

0.32

 outset

0.31

 starting

0.30

early

0.29

 Beginning

0.28

starting

0.27

Activations Density 0.177%

phrases indicating origins or beginnings

No Comments

No Known Activations