INDEX

Explanations

phrases related to visitor experiences and activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

æĶ¶åħ¥

-0.16

adero

-0.16

.scalablytyped

-0.16

 Invite

-0.15

isoft

-0.15

 commute

-0.15

urance

-0.15

elib

-0.15

reopen

-0.14

ellido

-0.14

POSITIVE LOGITS

 participate

0.26

 Particip

0.25

 purchase

0.23

 watch

0.23

 witness

0.22

 participates

0.22

 particip

0.21

 purchasing

0.20

 sample

0.20

 purchases

0.20

Activations Density 0.089%

phrases related to visitor experiences and activities

No Comments

No Known Activations