INDEX

Explanations

comparative phrases and expressions of expectation or belief

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 shouldn

-0.18

 weren

-0.16

ä¸įä¼ļ

-0.15

Ð¼ÐµÑĤÑĮ

-0.15

ulur

-0.15

 Didn

-0.15

 hasn

-0.14

æ±º

-0.14

 haven

-0.14

 doesn

-0.14

POSITIVE LOGITS

 barg

0.29

 bargain

0.23

 Barg

0.22

 bargaining

0.22

 realize

0.22

 realized

0.21

 realise

0.21

 realised

0.20

 realizes

0.19

 perhaps

0.19

Activations Density 0.054%

comparative phrases and expressions of expectation or belief

No Comments

No Known Activations