INDEX

Explanations

phrases expressing agreement or support in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ije

-0.16

ietet

-0.14

udget

-0.14

(TM

-0.14

zan

-0.14

etas

-0.13

smo

-0.13

arp

-0.13

adget

-0.13

Mam

-0.13

POSITIVE LOGITS

onia

0.17

avier

0.16

 coun

0.15

sÃŃ

0.15

onym

0.14

Fur

0.14

 Fake

0.14

.Debugger

0.14

avin

0.14

macen

0.14

Activations Density 0.022%

phrases expressing agreement or support in discussions

No Comments

No Known Activations