INDEX

Explanations

instances of the word "just" in relation to expressions of emotion or opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

isible

-0.15

utan

-0.15

oho

-0.15

ÌĨ

-0.15

ense

-0.14

raj

-0.14

 sanit

-0.14

tup

-0.14

itto

-0.13

ãĥĬãĥ«

-0.13

POSITIVE LOGITS

 simply

0.34

 Simply

0.27

Simply

0.25

 simplement

0.25

 plain

0.24

 prostÄĽ

0.23

 Ð¿ÑĢÐ¾ÑģÑĤÐ¾

0.22

 einfach

0.19

 overall

0.18

overall

0.18

Activations Density 0.134%

instances of the word "just" in relation to expressions of emotion or opinions

No Comments

No Known Activations