INDEX

Explanations

instances of demonstrative pronouns and phrases indicating emphasis or introduction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ullo

-0.15

Ñī

-0.15

apons

-0.13

nf

-0.13

ulent

-0.13

vr

-0.13

 STUD

-0.13

inous

-0.13

 ARGS

-0.13

glas

-0.13

POSITIVE LOGITS

 wasn

0.20

was

0.18

 soon

0.18

_was

0.17

 incident

0.16

same

0.16

#__

0.16

åĽº

0.16

 marked

0.15

å½ĵçĦ¶

0.15

Activations Density 0.119%

instances of demonstrative pronouns and phrases indicating emphasis or introduction

No Comments

No Known Activations