INDEX

Explanations

conversations and quotes related to political authority and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Computed

-0.14

 finally

-0.14

.loaded

-0.13

.tell

-0.13

ayer

-0.13

 Replies

-0.13

 ourselves

-0.13

 tell

-0.13

íĻĶ

-0.13

 Married

-0.13

POSITIVE LOGITS

 urged

0.28

 warned

0.28

 called

0.26

 cautioned

0.26

 hinted

0.26

 vowed

0.24

 noted

0.22

 stressed

0.22

 insisted

0.22

 thanked

0.21

Activations Density 0.100%

conversations and quotes related to political authority and governance

No Comments

No Known Activations