INDEX

Explanations

references to language learning applications and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

âĢ¦↵

-0.28

 âĢ¦↵

-0.23

âĢ¦and

-0.22

âĢ¦”

-0.22

 [âĢ¦]↵

-0.22

âĢ¦

-0.21

âĢ¦"

-0.20

âĢ¦.

-0.19

âĢ¦âĢ¦

-0.19

âĢ¦I

-0.19

POSITIVE LOGITS

#af

0.15

/***/

0.14

#ab

0.14

#ad

0.13

/******/

0.13

#ac

0.13

)frame

0.13

-wsj

0.13

)application

0.12

'gc

0.12

Activations Density 87.815%

references to language learning applications and their features

No Comments

No Known Activations