INDEX

Explanations

the word "then" 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 @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 then

-0.37

then

-0.33

 THEN

-0.26

 Then

-0.26

Then

-0.26

THEN

-0.26

 entonces

-0.25

_then

-0.25

	then

-0.23

 alors

-0.22

POSITIVE LOGITS

umber

0.28

ew

0.24

-President

0.19

 latter

0.19

ews

0.19

abouts

0.18

-current

0.18

/current

0.18

egative

0.17

ormal

0.16

Activations Density 0.087%

the word "then" in various contexts

No Comments

No Known Activations