INDEX

Explanations

complex arguments and perspectives in academic discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 elucid

-0.20

Narr

-0.15

urv

-0.14

oplay

-0.14

 Narrative

-0.14

 Trot

-0.14

 Talks

-0.14

 Lists

-0.14

ottie

-0.14

åĢ«

-0.13

POSITIVE LOGITS

exam

0.33

 examine

0.31

 examines

0.29

 examination

0.29

 explores

0.27

 explore

0.27

 examined

0.26

 chart

0.25

 Examination

0.25

 consideration

0.24

Activations Density 0.118%

complex arguments and perspectives in academic discourse

No Comments

No Known Activations