INDEX

Explanations

phrases that indicate comparisons or evaluations of concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 exist

-0.19

aran

-0.18

zsche

-0.18

Exist

-0.17

exists

-0.15

 existence

-0.15

 exists

-0.15

ugo

-0.15

exist

-0.15

 Exist

-0.15

POSITIVE LOGITS

addock

0.17

 concerned

0.17

edReader

0.16

ł

0.15

YN

0.15

odyn

0.14

bcc

0.14

abus

0.14

ivas

0.14

iffies

0.14

Activations Density 0.043%

phrases that indicate comparisons or evaluations of concepts

No Comments

No Known Activations