INDEX

Explanations

expressions of gratitude and recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

claimed

-0.15

 maybe

-0.15

 EITHER

-0.14

ëĭ´

-0.14

 only

-0.14

 Only

-0.13

 ONLY

-0.13

Only

-0.13

ãģĹãģĭ

-0.13

 either

-0.13

POSITIVE LOGITS

 everyone

0.40

 everybody

0.34

everyone

0.32

 Everyone

0.25

Everyone

0.25

 those

0.23

 countless

0.20

 past

0.19

those

0.19

 semua

0.19

Activations Density 0.135%

expressions of gratitude and recognition

No Comments

No Known Activations