INDEX

Explanations

phrases related to demonstrating or establishing one's abilities or worth

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

:///

-0.17

sville

-0.15

åĻ¨

-0.15

ÄįÃŃ

-0.15

kus

-0.15

krit

-0.14

Tow

-0.14

Ring

-0.14

packageName

-0.14

POSITIVE LOGITS

aris

0.16

aco

0.15

 bron

0.15

¹

0.15

osterone

0.14

 GÃ¼n

0.14

.NewRequest

0.14

_PATCH

0.14

 targ

0.14

 Spiel

0.13

Activations Density 0.104%

phrases related to demonstrating or establishing one's abilities or worth

No Comments

No Known Activations