INDEX

Explanations

occurrences of the article "a" and its variations

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

 Agents

-0.23

 Applications

-0.23

 Actions

-0.22

Events

-0.22

 Accounts

-0.22

 Activities

-0.22

 Animals

-0.22

 Events

-0.21

 Associates

-0.21

Agents

-0.21

POSITIVE LOGITS

Lot

0.22

Few

0.21

 Different

0.19

 Longer

0.19

 Successful

0.18

 Larger

0.18

 Truly

0.18

 Huge

0.18

 Powerful

0.18

 Lovely

0.17

Activations Density 0.080%

occurrences of the article "a" and its variations

No Comments

No Known Activations