INDEX

Explanations

mentions of "latest" or "latest news" related to various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 recent

-0.19

 lately

-0.19

 latest

-0.18

 recently

-0.16

 Latest

-0.15

 further

-0.15

ately

-0.14

uate

-0.14

uck

-0.14

 earlier

-0.14

POSITIVE LOGITS

0.30

-generation

0.28

 addition

0.27

 iteration

0.24

 additions

0.23

/current

0.22

 batch

0.21

 Addition

0.21

 developments

0.21

 generation

0.21

Activations Density 0.021%

mentions of "latest" or "latest news" related to various topics

No Comments

No Known Activations