INDEX

Explanations

expressions of affirmation and enthusiasm

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

ada

-0.19

EAR

-0.17

enuity

-0.15

afil

-0.14

INED

-0.14

atta

-0.14

æŃ¦åĻ¨

-0.14

 Maple

-0.14

ADA

-0.13

POSITIVE LOGITS

kers

0.17

¼

0.15

elic

0.14

arth

0.14

eyh

0.14

olec

0.14

iele

0.14

 bolt

0.13

.ActionListener

0.13

 shift

0.13

Activations Density 0.145%

expressions of affirmation and enthusiasm

No Comments

No Known Activations