INDEX

Explanations

phrases or statements expressing caution or warning

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

if

-0.19

uye

-0.16

msp

-0.16

 ÐµÑģÐ»Ð¸

-0.15

ledon

-0.14

ettel

-0.14

 enim

-0.14

ayd

-0.14

utar

-0.14

á»ĳi

-0.14

POSITIVE LOGITS

 chances

0.42

 odds

0.35

 then

0.35

then

0.34

 thÃ¬

0.29

 consider

0.28

 entonces

0.27

 Odds

0.26

çļĦè¯Ŀ

0.26

 Then

0.25

Activations Density 0.070%

phrases or statements expressing caution or warning

No Comments

No Known Activations