INDEX

Explanations

references to additions or modifications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ãĥ³ãĥĲ

-0.15

uguay

-0.14

izr

-0.14

Ä©

-0.14

Ø·ÙĬ

-0.14

¤íĶĦ

-0.13

 Lennon

-0.13

obil

-0.13

ismet

-0.13

 Angiospermae

-0.13

POSITIVE LOGITS

 addition

0.46

 added

0.45

 additions

0.42

 thÃªm

0.41

 additional

0.41

 ì¶Ķê°Ģ

0.40

 adds

0.39

 Addition

0.38

 adding

0.37

 Added

0.37

Activations Density 0.236%

references to additions or modifications in various contexts

No Comments

No Known Activations