INDEX

Explanations

references to academic works and citations in a research context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

èŃľ

-0.17

åĥ

-0.15

 XuÃ¢n

-0.14

 Transcript

-0.13

umpt

-0.13

 Scri

-0.13

 verge

-0.13

iegel

-0.13

SCREEN

-0.13

utor

-0.13

POSITIVE LOGITS

 surveys

0.29

 references

0.29

 reviews

0.28

 survey

0.28

 review

0.26

reviews

0.26

 chapter

0.24

 recent

0.24

references

0.24

survey

0.23

Activations Density 0.036%

references to academic works and citations in a research context

No Comments

No Known Activations