INDEX

Explanations

structured content related to publications and articles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

’

-0.19

ä¹ĭä¸Ģ

-0.17

-0.16

ongo

-0.16

ts

-0.15

lements

-0.14

alls

-0.14

 borders

-0.14

 escorte

-0.13

 siti

-0.13

POSITIVE LOGITS

ifter

0.22

0.17

osu

0.16

ghi

0.15

nap

0.15

è±Ĩ

0.15

database

0.14

-&

0.14

 ï¼

0.14

ï¼Ĩ

0.14

Activations Density 0.358%

structured content related to publications and articles

No Comments

No Known Activations