INDEX

Explanations

terms related to various fields and aspects of engineering

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

steller

-0.19

imitive

-0.15

eyh

-0.15

gether

-0.15

tery

-0.14

Ã«l

-0.14

gst

-0.14

kening

-0.14

LU

-0.14

ãĥ³ãĥĸ

-0.14

POSITIVE LOGITS

.scalablytyped

0.18

ered

0.18

/software

0.17

/engine

0.15

/disable

0.14

ipel

0.14

erson

0.14

ë³µì§Ģ

0.14

OTHER

0.14

vironment

0.13

Activations Density 0.023%

terms related to various fields and aspects of engineering

No Comments

No Known Activations