INDEX

Explanations

mentions of mixed qualities or characteristics 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 @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

urch

-0.16

uck

-0.16

bot

-0.15

peat

-0.15

por

-0.15

spot

-0.14

Ð¾Ð·ÐµÐ¼

-0.14

ESCO

-0.14

bia

-0.14

rale

-0.14

POSITIVE LOGITS

 mixed

0.31

 Mixed

0.30

mixed

0.29

Mixed

0.27

bag

0.26

 emotions

0.22

Bag

0.20

 Bless

0.19

æ··åĲĪ

0.19

Bag

0.19

Activations Density 0.018%

mentions of mixed qualities or characteristics in various contexts

No Comments

No Known Activations