INDEX

Explanations

references to paleontology and significant figures in that field

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

graf

-0.15

Æ¡

-0.15

enberg

-0.15

ersh

-0.15

rend

-0.14

ccione

-0.14

ieval

-0.14

 architecture

-0.13

assel

-0.13

adu

-0.13

POSITIVE LOGITS

 specimens

0.33

 specimen

0.32

 Natural

0.30

 collections

0.29

 museum

0.28

 Museum

0.28

Natural

0.27

zo

0.27

 natural

0.26

 museums

0.24

Activations Density 0.053%

references to paleontology and significant figures in that field

No Comments

No Known Activations