INDEX

Explanations

dialogue or quoted speech in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.85

Ùĩ

-0.45

ska

-0.37

sburg

-0.35

-0.30

sar

-0.30

sian

-0.29

sand

-0.28

à¤¨

-0.26

scape

-0.26

POSITIVE LOGITS

odore

0.29

atre

0.25

etheless

0.23

adays

0.20

ÑįÑĤÐ¾Ð¼Ñĥ

0.20

bsites

0.18

gether

0.18

gli

0.18

tlement

0.17

alog

0.17

Activations Density 0.128%

dialogue or quoted speech in the text

No Comments

No Known Activations