INDEX

Explanations

expressions of speculation or uncertainty

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

ambiguous

-0.15

ĮĢ

-0.14

oku

-0.14

 klar

-0.13

ux

-0.13

rzy

-0.13

olina

-0.13

hq

-0.12

(utf

-0.12

 ÑĩÐ¾Ð³Ð¾

-0.12

POSITIVE LOGITS

 because

0.32

åĽłä¸º

0.29

because

0.29

Because

0.27

 Because

0.26

due

0.26

 porque

0.25

due

0.24

ecause

0.23

 karena

0.22

Activations Density 0.253%

expressions of speculation or uncertainty

No Comments

No Known Activations