INDEX

Explanations

phrases and expressions related to experiences and outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

åĴ²

-0.17

ç¶ļ

-0.17

izik

-0.15

gere

-0.15

 å£

-0.14

 setAddress

-0.14

annon

-0.14

atte

-0.14

caffold

-0.14

itou

-0.14

POSITIVE LOGITS

 leaving

0.48

 leave

0.47

 emerge

0.41

 Leave

0.41

Leave

0.40

 emerged

0.39

 exit

0.39

leave

0.37

 leaves

0.37

 away

0.37

Activations Density 0.204%

phrases and expressions related to experiences and outcomes

No Comments

No Known Activations