INDEX

Explanations

references to mathematical theorems and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ewan

-0.18

 Stuff

-0.17

vell

-0.17

adden

-0.15

assi

-0.15

Stuff

-0.15

jvu

-0.14

åįĺ

-0.14

avin

-0.14

enheim

-0.14

POSITIVE LOGITS

 reviews

0.20

][

0.19

][]

0.17

 review

0.17

Reviewed

0.16

 discussion

0.16

see

0.16

 reviewed

0.15

sec

0.15

review

0.15

Activations Density 0.011%

references to mathematical theorems and equations

No Comments

No Known Activations