INDEX

Explanations

the phrase "that" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 ná»¯a

-0.15

meyi

-0.14

OwnProperty

-0.14

#echo

-0.13

uisse

-0.13

oice

-0.13

 rencont

-0.13

orelease

-0.13

oven

-0.12

rove

-0.12

POSITIVE LOGITS

 although

0.28

 while

0.24

 since

0.24

if

0.23

 unless

0.21

 despite

0.20

although

0.20

æĹ¢çĦ¶

0.19

 whereas

0.18

since

0.18

Activations Density 0.272%

the phrase "that" in various contexts

No Comments

No Known Activations