INDEX

Explanations

phrases indicating functionality and performance in applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 Stuart

-0.15

.scalablytyped

-0.15

icip

-0.15

endregion

-0.15

rezent

-0.14

.ends

-0.14

ghest

-0.14

oft

-0.14

_TYPEDEF

-0.14

icing

-0.13

POSITIVE LOGITS

istrovstvÃŃ

0.18

/false

0.15

ieri

0.15

 pari

0.14

 except

0.13

cheon

0.13

 ÏĢÎµÏģÎ¯

0.13

atch

0.13

draul

0.13

Activations Density 0.052%

phrases indicating functionality and performance in applications

No Comments

No Known Activations