INDEX

Explanations

names and titles associated with publishers and academic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 prime

-0.16

oney

-0.14

hiro

-0.14

ipeg

-0.14

 Nationals

-0.14

dre

-0.14

aland

-0.14

Ø£Ø³

-0.14

 envelope

-0.13

 contro

-0.13

POSITIVE LOGITS

 Press

0.35

Press

0.33

 press

0.32

press

0.29

 PRESS

0.27

 presses

0.27

_press

0.25

åĩºçīĪç¤¾

0.25

 Publishing

0.24

PRESS

0.23

Activations Density 0.158%

names and titles associated with publishers and academic references

No Comments

No Known Activations